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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative or alarming situations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with unsettling or alarming events and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á
    -0.81
    hement
    -0.78
    arten
    -0.77
    uay
    -0.77
    onso
    -0.76
    hips
    -0.73
    pring
    -0.72
    glas
    -0.71
     Router
    -0.71
     oun
    -0.70
    POSITIVE LOGITS
    ly
    0.97
    omic
    0.91
     revelations
    0.89
     Revelations
    0.87
     occurrences
    0.87
    ingly
    0.86
     trend
    0.85
     Trend
    0.84
     behaviour
    0.83
     similarities
    0.83
    Act Density 0.119%

    No Known Activations