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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a particular point in time

    oai_token-act-pair · gpt-3.5-turbo

    references to specific points in time or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twin
    -0.66
     twins
    -0.64
    english
    -0.63
    mir
    -0.62
    gem
    -0.60
     Cities
    -0.59
     sisters
    -0.59
    itary
    -0.58
    amaz
    -0.57
    harm
    -0.56
    POSITIVE LOGITS
     onwards
    0.78
     onward
    0.75
    cture
    0.74
    abouts
    0.71
    endment
    0.70
    ebin
    0.69
    points
    0.67
    ozo
    0.65
    itial
    0.64
    SPONSORED
    0.62
    Act Density 0.022%

    No Known Activations