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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to following rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compliance and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.77
    ENTS
    -0.77
    notes
    -0.76
    ouf
    -0.72
     pid
    -0.72
    posing
    -0.68
    ible
    -0.67
    ents
    -0.63
    jri
    -0.63
    ripp
    -0.61
    POSITIVE LOGITS
    ī
    1.00
    ģ
    0.89
    ĭ
    0.87
    Ħ
    0.81
    ı
    0.77
    otide
    0.75
    ¿½
    0.73
    Ĭ±
    0.72
    art
    0.71
    «
    0.71
    Act Density 0.070%

    No Known Activations