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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.98
    lgari
    -0.72
    expandindo
    -0.71
    ագրություններ
    -0.68
    ConstraintMaker
    -0.68
     виправивши
    -0.68
     tartalomajánló
    -0.66
     ainfi
    -0.65
     estekak
    -0.65
     avoient
    -0.65
    POSITIVE LOGITS
    olol
    0.56
    PropertyChanging
    0.42
     sign
    0.41
    respectively
    0.41
     list
    0.40
     अलावा
    0.39
    sig
    0.39
     mix
    0.39
    ...</
    0.38
    ----</
    0.38
    Act Density 0.547%

    No Known Activations