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

    Neuronpedia

    INDEX
    Explanations

    file paths

    oai_token-act-pair · gpt-3.5-turbo

    slashes or similar symbols indicating divisions or categories in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.76
     defe
    -0.69
    terday
    -0.67
     Grimes
    -0.64
     contender
    -0.63
    glers
    -0.62
    iguous
    -0.61
     skelet
    -0.59
     tender
    -0.59
    itated
    -0.58
    POSITIVE LOGITS
    ËĪ
    1.58
    usr
    1.10
    Film
    0.95
    u
    0.91
    etc
    0.91
    proc
    0.82
    tg
    0.82
    Applications
    0.80
    dayName
    0.80
    laughs
    0.78
    Act Density 0.023%

    No Known Activations