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

    Neuronpedia

    INDEX
    Explanations

    instances of perceived social judgment and perceived negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CEEDED
    -0.15
     bod
    -0.14
    éĮ
    -0.14
    bak
    -0.14
    accessible
    -0.14
    assi
    -0.14
     poss
    -0.14
    /generated
    -0.14
    choice
    -0.13
    _MODULE
    -0.13
    POSITIVE LOGITS
    ayer
    0.16
    iband
    0.16
     cé
    0.14
    inou
    0.13
    240
    0.13
    916
    0.13
    å±ĭ
    0.13
    anye
    0.13
     glyphicon
    0.13
    strap
    0.13
    Act Density 0.166%

    No Known Activations