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

    Neuronpedia

    INDEX
    Explanations

    female names

    oai_token-act-pair · gpt-3.5-turbo

    names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ribution
    -0.79
    Magikarp
    -0.72
    DEN
    -0.71
    Ħ¢
    -0.70
    ictionary
    -0.66
    ARD
    -0.63
    gets
    -0.63
     contiguous
    -0.62
     overse
    -0.62
    PDATE
    -0.61
    POSITIVE LOGITS
    ption
    0.86
     Lazarus
    0.85
     Watson
    0.78
    otte
    0.76
    ogen
    0.76
    ione
    0.75
    itable
    0.75
    ury
    0.75
    illian
    0.74
    ual
    0.73
    Act Density 0.012%

    No Known Activations