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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reasons or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hammad
    -0.63
    olen
    -0.61
    oster
    -0.61
    antine
    -0.59
    angelo
    -0.57
    nings
    -0.55
    MSN
    -0.55
    fired
    -0.55
    jen
    -0.54
    wd
    -0.53
    POSITIVE LOGITS
     reasons
    1.39
     reason
    1.27
    etheless
    0.92
     Reasons
    0.90
     awhile
    0.85
     certain
    0.83
     WAY
    0.82
    reason
    0.77
     ways
    0.77
     milliseconds
    0.77
    Act Density 0.402%

    No Known Activations