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

    Neuronpedia

    INDEX
    Explanations

    expressions of frankness or honesty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.82
     nakalista
    -0.80
    apunov
    -0.68
    Tracce
    -0.68
    PMailer
    -0.63
     automatiquement
    -0.61
    #+#
    -0.61
     localObject
    -0.60
    tagHelper
    -0.60
    })));
    -0.59
    POSITIVE LOGITS
    Frankly
    0.87
     frankly
    0.86
     blunt
    0.86
     straightforward
    0.83
     honestly
    0.80
     bluntly
    0.79
     honest
    0.78
     simple
    0.75
     plain
    0.72
     frank
    0.71
    Act Density 0.410%

    No Known Activations