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

    Neuronpedia

    INDEX
    Explanations

    timestamps of when information was posted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Posted" followed by a timestamp

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.89
    ively
    -0.80
    ivo
    -0.78
    fitting
    -0.76
    isky
    -0.75
    ishi
    -0.73
    oller
    -0.72
    finder
    -0.68
    ppard
    -0.68
    osc
    -0.66
    POSITIVE LOGITS
    monton
    0.76
    vertis
    0.74
    itors
    0.72
    MON
    0.70
     Tue
    0.67
    Thu
    0.66
     Written
    0.65
     Thu
    0.65
    Posted
    0.65
    escription
    0.63
    Act Density 0.017%

    No Known Activations