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

    Neuronpedia

    INDEX
    Explanations

    the name "Kamala" and its variants

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ala" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lines
    -0.87
    line
    -0.86
    ly
    -0.86
    lies
    -0.85
    LY
    -0.84
    liness
    -0.83
    manship
    -0.83
    lessly
    -0.82
    dit
    -0.81
    lers
    -0.79
    POSITIVE LOGITS
    ibaba
    1.10
    uthor
    1.08
    emia
    1.04
     Pradesh
    0.95
    qua
    0.93
    isa
    0.89
    pha
    0.84
    velength
    0.83
    ensis
    0.83
    ala
    0.82
    Act Density 0.018%

    No Known Activations