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

    Neuronpedia

    INDEX
    Explanations

    phrases related to excessiveness or extremes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to excessive action or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.77
    isons
    -0.76
    ptions
    -0.71
    tex
    -0.70
    çĶŁ
    -0.70
     Toro
    -0.69
    Tex
    -0.69
    ãĤ«
    -0.69
    ãĥĥ
    -0.69
    ãĤ§
    -0.66
    POSITIVE LOGITS
    xual
    0.93
    alach
    0.84
    cephal
    0.80
     overboard
    0.79
    agall
    0.79
    ItemTracker
    0.78
    FontSize
    0.76
    forward
    0.76
    quartered
    0.75
    idy
    0.75
    Act Density 0.030%

    No Known Activations