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

    Neuronpedia

    INDEX
    Explanations

    words related to the emotional or stylistic quality of communication

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of tone in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.76
    oppable
    -0.76
    heid
    -0.71
    axter
    -0.70
    minster
    -0.69
    essions
    -0.67
     Confederation
    -0.66
    ortun
    -0.65
    enium
    -0.65
    uthor
    -0.64
    POSITIVE LOGITS
     deaf
    1.18
     tone
    0.93
     Tone
    0.92
     dial
    0.81
     tones
    0.77
     emanating
    0.73
     softened
    0.70
     muted
    0.68
     shif
    0.67
     tune
    0.66
    Act Density 0.056%

    No Known Activations