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

    Neuronpedia

    INDEX
    Explanations

    terms related to rhetoric and rhetorical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rhetoric and discourses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numberWith
    -0.63
     Identi
    -0.55
     assi
    -0.53
     unif
    -0.53
     Identification
    -0.51
     asso
    -0.50
    Chance
    -0.48
    Identification
    -0.48
     Appro
    -0.47
    GLI
    -0.47
    POSITIVE LOGITS
     Rhetoric
    0.92
     rhetoric
    0.91
     discurso
    0.82
     discursos
    0.80
     débats
    0.77
     desmotivaciones
    0.73
     eloquence
    0.73
     discourse
    0.71
     balcón
    0.71
     Rhetor
    0.70
    Act Density 0.008%

    No Known Activations