Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    keywords related to technological devices and complex systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to assassination and derived terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.35
    3:0.06
    4:0.13
    5:0.05
    6:0.03
    7:0.03
    8:0.06
    9:0.09
    10:0.06
    11:0.03
    Negative Logits
    falls
    -1.38
     sshd
    -1.31
    Subscribe
    -1.26
    ................
    -1.26
    fork
    -1.22
    iatrics
    -1.21
    ebin
    -1.16
    Xi
    -1.15
     captcha
    -1.14
    acceptable
    -1.11
    POSITIVE LOGITS
    uration
    1.41
    ーテ
    1.33
    eering
    1.31
    pta
    1.30
    ciating
    1.27
     Lauder
    1.22
     Miz
    1.21
     Templ
    1.20
     Monte
    1.20
     Akin
    1.20
    Act Density 0.011%

    No Known Activations