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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing uncertainty or self-reflection

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.76
     Biôgrafia
    -0.61
    WireFormatLite
    -0.61
    tagHelperRunner
    -0.60
    exitRule
    -0.56
    LookAnd
    -0.54
     rhestr
    -0.54
    NameInMap
    -0.53
    localctx
    -0.52
    AccessorTable
    -0.52
    POSITIVE LOGITS
     Sélectionnez
    0.64
    Continue
    0.57
     […]
    0.57
    bini
    0.55
     …
    0.53
    rizona
    0.51
    
    0.51
     [...]
    0.50
     通販
    0.50
    ":[{
    0.50
    Act Density 1.048%

    No Known Activations