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

    Neuronpedia

    INDEX
    Explanations

    names of people or places related to the military or political context

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     breath
    -0.80
     Carbuncle
    -0.78
    imately
    -0.74
    dash
    -0.71
    ģĸ
    -0.71
     cheek
    -0.70
    sembly
    -0.68
     retri
    -0.67
    aminer
    -0.67
    76561
    -0.67
    POSITIVE LOGITS
    ulia
    0.82
    acist
    0.79
    den
    0.76
    atility
    0.76
    orius
    0.74
    locks
    0.74
    uca
    0.74
    atile
    0.72
    eon
    0.72
    ulla
    0.72
    Act Density 0.042%

    No Known Activations