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

    Neuronpedia

    INDEX
    Explanations

    statements related to impactful or significant events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to being emotionally or physically disturbed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hib
    -0.86
    ouf
    -0.83
    endi
    -0.83
    ators
    -0.72
    elaide
    -0.69
    emis
    -0.69
    osal
    -0.68
    á
    -0.68
    iler
    -0.68
    missible
    -0.67
    POSITIVE LOGITS
    DAQ
    0.85
     rocked
    0.77
     tremend
    0.74
    wave
    0.71
     silence
    0.70
     rocking
    0.70
     apart
    0.66
    DOWN
    0.65
    waves
    0.64
     shaken
    0.64
    Act Density 0.014%

    No Known Activations