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

    Neuronpedia

    INDEX
    Explanations

    words related to negative impacts or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to harmful effects or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatrics
    -0.77
    arte
    -0.76
    omet
    -0.73
    ordan
    -0.72
    gio
    -0.71
    batch
    -0.71
    ETF
    -0.70
    chan
    -0.70
    ea
    -0.68
    ilk
    -0.68
    POSITIVE LOGITS
     undermin
    0.97
     havoc
    0.91
     shocks
    0.83
     damage
    0.82
     damaging
    0.79
     liqu
    0.77
     warheads
    0.77
     adolesc
    0.76
     blows
    0.76
     spells
    0.76
    Act Density 0.014%

    No Known Activations