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

    Neuronpedia

    INDEX
    Explanations

    words related to negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to loss or its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTS
    -0.70
     inventive
    -0.68
    ATT
    -0.66
    rouse
    -0.65
    ECK
    -0.63
     dotted
    -0.62
    thodox
    -0.62
    ":[{"
    -0.62
    ansky
    -0.61
     Occupations
    -0.61
    POSITIVE LOGITS
     loss
    1.11
     Loss
    1.06
    loss
    1.04
     aversion
    0.97
    iem
    0.89
     losses
    0.89
    byss
    0.82
     experien
    0.73
     landfall
    0.73
    luster
    0.72
    Act Density 0.010%

    No Known Activations