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

    Neuronpedia

    INDEX
    Explanations

    the name "Tara."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -2.18
    ĵ
    -2.02
     \%
    -1.99
    Īĺ
    -1.95
    ı
    -1.85
     ?"
    -1.63
    Ħ
    -1.62
    uric
    -1.61
    ĥ½
    -1.59
    '?"
    -1.59
    POSITIVE LOGITS
    esan
    1.79
    ist
    1.79
    istic
    1.76
    bank
    1.73
    iste
    1.70
    wn
    1.70
    keeping
    1.68
    vity
    1.68
     flic
    1.67
    enstein
    1.66
    Act Density 0.020%

    No Known Activations