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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the concepts of positivity and negativity in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.17
    ë°ĺ
    -0.15
     Kahn
    -0.15
    ocus
    -0.15
    ogo
    -0.14
    .GetValue
    -0.14
    ason
    -0.14
     vibr
    -0.14
    ESIS
    -0.14
     pret
    -0.14
    POSITIVE LOGITS
    blank
    0.16
     outnumber
    0.15
    unnel
    0.15
     harmful
    0.15
     Disp
    0.14
     trai
    0.14
     Brave
    0.14
    andro
    0.14
    елÑĸв
    0.14
    Cre
    0.14
    Act Density 0.282%

    No Known Activations