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

    Neuronpedia

    INDEX
    Explanations

    words related to a particular theme that includes "ire," possibly related to anger or fire

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "fire" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļé
    -0.92
    ĸļ
    -0.89
     carbohyd
    -0.84
     cellul
    -0.79
    ¬¼
    -0.78
    ĨĴ
    -0.77
    romeda
    -0.73
    Īè
    -0.72
    acca
    -0.72
    achusetts
    -0.72
    POSITIVE LOGITS
    nces
    1.07
    lli
    0.96
    ttes
    0.89
    cia
    0.89
    lessly
    0.87
    ly
    0.84
    lette
    0.82
    lich
    0.79
    les
    0.78
    zza
    0.78
    Act Density 0.016%

    No Known Activations