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

    Neuronpedia

    INDEX
    Explanations

    words related to psychological or emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cognitive challenges and social criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.80
    hered
    -0.75
    bilt
    -0.75
    FactoryReloaded
    -0.73
    spective
    -0.69
    20439
    -0.68
    çīĪ
    -0.66
     DISTRICT
    -0.66
     brow
    -0.65
    lif
    -0.64
    POSITIVE LOGITS
    ances
    1.17
    ant
    1.12
    ance
    1.08
    antly
    1.05
    ante
    0.94
    antes
    0.93
    arium
    0.89
    atory
    0.88
    inated
    0.88
    ants
    0.86
    Act Density 0.048%

    No Known Activations