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

    Neuronpedia

    INDEX
    Explanations

    newsletter titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Brief" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pez
    -0.80
    CE
    -0.78
    artifacts
    -0.75
    SEA
    -0.72
     technologically
    -0.71
    GO
    -0.70
    tackle
    -0.68
    OURCE
    -0.68
    OPE
    -0.67
    âĹ¼
    -0.65
    POSITIVE LOGITS
    cases
    1.13
    case
    1.02
    ing
    0.95
     Brief
    0.94
    itude
    0.87
    ly
    0.87
    rief
    0.87
    emort
    0.87
    escription
    0.86
    ings
    0.82
    Act Density 0.005%

    No Known Activations