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

    Neuronpedia

    INDEX
    Explanations

    words related to societal concepts, settings, and activities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal structures and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cause
    -0.62
    Cause
    -0.60
    trigger
    -0.55
    antz
    -0.55
     yr
    -0.55
    Tags
    -0.55
    rosse
    -0.54
    inqu
    -0.53
    ————————————————
    -0.53
     intertw
    -0.53
    POSITIVE LOGITS
     meanwhile
    0.92
    lance
    0.81
     however
    0.72
     there
    0.69
     nutshell
    0.68
    occupied
    0.65
    ç¥ŀ
    0.62
     Pathfinder
    0.61
     Sham
    0.61
    achy
    0.59
    Act Density 0.575%

    No Known Activations