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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the actions of objects or subjects

    oai_token-act-pair · gpt-3.5-turbo

    numerical expressions and significant values related to events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.60
    cffff
    -0.57
    GROUP
    -0.56
    items
    -0.55
    @#&
    -0.55
    avid
    -0.55
    cised
    -0.55
    enta
    -0.53
    HAEL
    -0.52
    cussion
    -0.50
    POSITIVE LOGITS
     its
    0.87
     itself
    0.87
     ITS
    0.83
    Its
    0.70
     decom
    0.69
     evolve
    0.68
     outper
    0.67
     undergone
    0.66
     Its
    0.65
     autonom
    0.64
    Act Density 1.202%

    No Known Activations