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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative events or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with failures, shortages, and negative impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    augh
    -0.64
    Fair
    -0.58
    Cho
    -0.58
    agog
    -0.56
    eva
    -0.52
     expresses
    -0.52
     carrot
    -0.52
    gger
    -0.51
    Vs
    -0.51
    Hop
    -0.51
    POSITIVE LOGITS
    smanship
    0.67
    uitous
    0.64
    aution
    0.63
    alore
    0.62
     stemming
    0.61
    pection
    0.60
    imal
    0.60
    oldown
    0.59
    oslav
    0.59
     destro
    0.59
    Act Density 0.384%

    No Known Activations