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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical attributes or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with physical conditions and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungle
    -0.74
    adish
    -0.73
    stellar
    -0.72
    quist
    -0.69
    tower
    -0.69
     Boe
    -0.68
    Gate
    -0.67
    uden
    -0.65
    ources
    -0.65
     Gos
    -0.64
    POSITIVE LOGITS
    ity
    1.02
     manifestation
    0.99
     altercation
    0.98
     impossibility
    0.98
     ailments
    0.87
     embodiment
    0.86
    ized
    0.86
    ité
    0.84
     disabilities
    0.84
     therapists
    0.84
    Act Density 0.046%

    No Known Activations