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

    Neuronpedia

    INDEX
    Explanations

    mentions of organizations and specific names of people

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >[
    -0.85
    physical
    -0.74
    poke
    -0.71
    lust
    -0.68
    ibo
    -0.66
    ital
    -0.66
    albeit
    -0.65
    needed
    -0.63
    nikov
    -0.63
    imil
    -0.63
    POSITIVE LOGITS
     thence
    1.07
     Associates
    0.90
     thereby
    0.85
     consequently
    0.82
     assorted
    0.82
     subsequently
    0.77
     onwards
    0.75
     thus
    0.74
     vice
    0.73
     hence
    0.72
    Act Density 0.383%

    No Known Activations