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

    Neuronpedia

    INDEX
    Explanations

    verbs related to speech, particularly those indicating communication or expression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "voicing" and its variations, indicating expressions of opinion or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jer
    -0.75
    ijn
    -0.66
    ination
    -0.65
     Journals
    -0.64
    icz
    -0.62
    leans
    -0.62
    inals
    -0.61
    inness
    -0.61
    fet
    -0.60
     Lust
    -0.59
    POSITIVE LOGITS
     voices
    0.92
     chords
    0.92
    unci
    0.91
    DonaldTrump
    0.91
     voic
    0.86
     voiced
    0.86
     voicing
    0.81
    unciation
    0.80
     voice
    0.78
    anche
    0.77
    Act Density 0.022%

    No Known Activations