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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and information sources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media and digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Britann
    -0.65
     Civilization
    -0.63
     speech
    -0.63
     heel
    -0.63
     arsen
    -0.63
     ANG
    -0.63
     commencement
    -0.62
     elev
    -0.61
     defense
    -0.61
     Canary
    -0.61
    POSITIVE LOGITS
    coins
    0.95
    sand
    0.88
    dit
    0.86
    info
    0.85
    nr
    0.84
    fen
    0.82
    erie
    0.82
    nik
    0.81
    eks
    0.79
    widget
    0.78
    Act Density 0.275%

    No Known Activations