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

    Neuronpedia

    INDEX
    Explanations

    the names of individuals, specifically those mentioned frequently in a conversational or narrative context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    '},
    -0.86
    '){
    -0.85
    "){
    -0.82
     /**
    -0.79
    Hok
    -0.77
     Steiner
    -0.76
    =$((
    -0.75
    UnsafeEnabled
    -0.73
    Datuak
    -0.73
     Segal
    -0.71
    POSITIVE LOGITS
     Dave
    0.89
    Dave
    0.88
    gebob
    0.88
    Bob
    0.83
     Bob
    0.81
    dave
    0.73
     Joe
    0.72
    Sue
    0.72
    Joe
    0.71
     Jim
    0.68
    Act Density 0.049%

    No Known Activations