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

    Neuronpedia

    INDEX
    Explanations

    phrases or verbs indicating calls to action or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.18
    3:0.07
    4:0.03
    5:0.13
    6:0.03
    7:0.02
    8:0.07
    9:0.23
    10:0.07
    11:0.03
    Negative Logits
    ゼウス
    -1.48
    サ
    -1.28
    �
    -1.28
     approximation
    -1.25
     Spur
    -1.24
     steroids
    -1.23
     miscarriage
    -1.20
     centerpiece
    -1.19
     dystop
    -1.19
    lag
    -1.18
    POSITIVE LOGITS
     Idle
    1.32
    ername
    1.30
    haw
    1.29
    iris
    1.28
     clergy
    1.26
     waivers
    1.24
    swick
    1.22
     wiser
    1.22
     Vel
    1.21
    hement
    1.21
    Act Density 0.073%

    No Known Activations