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

    Neuronpedia

    INDEX
    Explanations

    special characters indicating emphasis or a break in text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viron
    -0.83
    zona
    -0.79
    nings
    -0.77
    gers
    -0.77
    ciating
    -0.76
    keepers
    -0.72
    chnology
    -0.71
    tto
    -0.71
    ctions
    -0.71
    ndra
    -0.66
    POSITIVE LOGITS
    ÑĮ
    0.96
    åĭ
    0.77
    ial
    0.77
    alon
    0.76
    ipl
    0.75
    âĶģ
    0.74
    ħ
    0.74
    issions
    0.73
    ury
    0.73
    orrow
    0.73
    Act Density 0.005%

    No Known Activations