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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happened" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tan
    -0.90
    oyal
    -0.83
    uffed
    -0.82
    entric
    -0.81
    hart
    -0.77
    mens
    -0.77
    illusion
    -0.76
    ench
    -0.76
    ofer
    -0.74
    rylic
    -0.74
    POSITIVE LOGITS
     unfolding
    0.79
     Procedure
    0.78
     happened
    0.76
     yesterday
    0.76
     wrong
    0.72
     Myster
    0.71
     Ukrain
    0.71
     occ
    0.71
     perpetrated
    0.71
     Pax
    0.70
    Act Density 0.037%

    No Known Activations