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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases that assert opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     getopt
    -0.56
     Bowden
    -0.51
     địa
    -0.50
    zji
    -0.49
    core
    -0.49
    országban
    -0.48
    哒
    -0.48
     Зачем
    -0.48
     umano
    -0.48
    Core
    -0.48
    POSITIVE LOGITS
    EndContext
    0.82
    ConstraintMaker
    0.81
    ArrowToggle
    0.70
    可以说是
    0.67
     ProtoMessage
    0.64
    也算是
    0.62
    ỡng
    0.59
     HasFactory
    0.59
    --
    0.58
     endblock
    0.58
    Act Density 0.233%

    No Known Activations