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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to impactful news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issen
    -0.18
    sert
    -0.16
    ÏĦÏį
    -0.16
    atz
    -0.15
     sobie
    -0.15
     Bair
    -0.15
    cobra
    -0.14
    ẫu
    -0.14
    cuda
    -0.14
     rost
    -0.14
    POSITIVE LOGITS
     shock
    0.35
     waves
    0.31
     wave
    0.26
     Shock
    0.25
    Shock
    0.25
     rever
    0.24
     trem
    0.23
     into
    0.23
    wave
    0.22
     sh
    0.21
    Act Density 0.019%

    No Known Activations