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

    Neuronpedia

    INDEX
    Explanations

    negative clauses indicating absence or denial

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gnu
    -0.68
    Preview
    -0.67
     Traps
    -0.66
    ULAR
    -0.65
    trap
    -0.65
    ships
    -0.63
     Mushroom
    -0.60
    enos
    -0.59
    kind
    -0.59
    ãĥį
    -0.58
    POSITIVE LOGITS
    wegian
    1.11
     nor
    0.86
    hovah
    0.86
    berto
    0.78
     Lumpur
    0.74
    theless
    0.73
     shalt
    0.71
    fleet
    0.70
    withstanding
    0.67
    onso
    0.67
    Act Density 0.010%

    No Known Activations