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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe similarities or comparisons between different things

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or instances where similarity is expressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Published
    -0.71
    rection
    -0.68
    UFF
    -0.60
    oway
    -0.60
    ale
    -0.59
    ARD
    -0.59
    ribution
    -0.59
     Bild
    -0.59
    adh
    -0.57
     Lauderdale
    -0.57
    POSITIVE LOGITS
    lihood
    1.18
     minded
    0.85
    worldly
    0.85
    icut
    0.84
    ively
    0.83
    etheless
    0.83
    minded
    0.82
     twins
    0.82
    quartered
    0.79
    ities
    0.78
    Act Density 0.041%

    No Known Activations