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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events being performed on something

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions related to societal issues or systemic failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Founding
    -0.69
    assies
    -0.62
     descended
    -0.60
    ierre
    -0.59
     Falling
    -0.58
     CLS
    -0.58
     Anders
    -0.56
     Shining
    -0.55
    otaur
    -0.55
     reunited
    -0.55
    POSITIVE LOGITS
     by
    0.95
     elsewhere
    0.81
    ynamic
    0.79
    .</
    0.75
    igated
    0.75
     prominently
    0.75
     unintention
    0.74
     through
    0.74
     inconsist
    0.73
    .–
    0.73
    Act Density 0.335%

    No Known Activations