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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    collective actions or sentiments expressed by a group of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.71
    Ü
    -0.64
    ancial
    -0.63
     Roundup
    -0.63
     Athletics
    -0.61
     frontman
    -0.58
     Notting
    -0.58
    _-
    -0.57
     Bounty
    -0.57
     Patriarch
    -0.57
    POSITIVE LOGITS
    nai
    0.79
    ilers
    0.74
    ometric
    0.73
    conom
    0.71
    orah
    0.70
    horn
    0.70
    seys
    0.68
    owers
    0.67
    need
    0.67
    wat
    0.65
    Act Density 0.315%

    No Known Activations