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

    Neuronpedia

    INDEX
    Explanations

    words related to causing problems or chaos

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative impacts or issues arising from various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estone
    -0.69
    estones
    -0.65
    aucas
    -0.64
    £ı
    -0.64
     Witcher
    -0.62
    omorphic
    -0.61
     mature
    -0.60
     carrot
    -0.59
    hent
    -0.59
     reformed
    -0.58
    POSITIVE LOGITS
     havoc
    0.82
     unnecessarily
    0.73
     depending
    0.63
    iffin
    0.62
     Venezuel
    0.61
     morale
    0.61
     Judd
    0.60
    hole
    0.59
     akin
    0.59
     Jagu
    0.58
    Act Density 0.366%

    No Known Activations