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

    Neuronpedia

    INDEX
    Explanations

    character names and their associated attributes or powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     good
    -0.66
     deltaTime
    -0.61
     Good
    -0.60
    Bara
    -0.58
     place
    -0.56
     CLAR
    -0.56
     Sharp
    -0.55
     Yap
    -0.55
    Good
    -0.54
    بالإنجليزية
    -0.54
    POSITIVE LOGITS
    AnchorStyles
    0.89
    panto
    0.84
     Morav
    0.83
     protoimpl
    0.83
    PreferredItem
    0.82
     >=",
    0.81
     Leth
    0.79
     pallets
    0.78
    ConstraintMaker
    0.78
     선수
    0.77
    Act Density 1.728%

    No Known Activations