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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical attributes or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to physical aspects or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ered
    -0.75
    adish
    -0.74
    bare
    -0.72
    gd
    -0.72
    quist
    -0.71
    ungle
    -0.70
    tower
    -0.67
    glers
    -0.67
    poon
    -0.67
    uden
    -0.67
    POSITIVE LOGITS
     manifestation
    0.98
    ity
    0.95
     sciences
    0.88
     impossibility
    0.87
    ized
    0.87
     manifestations
    0.85
    anguage
    0.85
     altercation
    0.84
     necessities
    0.83
    isation
    0.80
    Act Density 0.018%

    No Known Activations