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

    Neuronpedia

    INDEX
    Explanations

    information related to success or performance in a specific field or domain

    oai_token-act-pair · gpt-3.5-turbo

    references to "field."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.79
    Priv
    -0.74
    bian
    -0.74
     BaseType
    -0.71
    ILA
    -0.70
    ilyn
    -0.69
    DIT
    -0.69
    ï¸
    -0.64
     Seas
    -0.63
    doms
    -0.63
    POSITIVE LOGITS
    plane
    0.81
    field
    0.81
    grass
    0.80
    cloth
    0.80
    keepers
    0.77
    keeping
    0.75
    side
    0.74
    ftime
    0.72
    idable
    0.72
    fields
    0.72
    Act Density 0.018%

    No Known Activations