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

    Neuronpedia

    INDEX
    Explanations

    physical attributes or actions, particularly focusing on physicality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physicality and physical states or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ered
    -0.76
    ungle
    -0.74
    adish
    -0.74
     Gos
    -0.70
    later
    -0.70
     Parables
    -0.69
    INTON
    -0.68
    bare
    -0.68
    stellar
    -0.68
     Unch
    -0.65
    POSITIVE LOGITS
     altercation
    0.93
    ity
    0.90
     therapists
    0.87
     impossibility
    0.83
     disabilities
    0.80
    ities
    0.80
     manifestation
    0.80
     ailments
    0.78
     barriers
    0.77
     prowess
    0.77
    Act Density 0.014%

    No Known Activations