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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical equipment or tools

    oai_token-act-pair · gpt-3.5-turbo

    references to various entities and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.76
    will
    -0.68
    Will
    -0.65
    osen
    -0.64
    shall
    -0.63
    emonic
    -0.60
     will
    -0.60
    fourth
    -0.60
    Ô
    -0.58
    catentry
    -0.58
    POSITIVE LOGITS
     consisted
    1.70
     resembled
    1.59
     lacked
    1.47
     smelled
    1.47
     seemed
    1.46
     differed
    1.38
     tended
    1.38
     hadn
    1.36
     looked
    1.32
     belonged
    1.31
    Act Density 0.565%

    No Known Activations