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

    Neuronpedia

    INDEX
    Explanations

    instances of honesty and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppBundle
    -0.62
    =’
    -0.60
    PMailer
    -0.58
    aguya
    -0.57
     Teach
    -0.56
     kanya
    -0.56
     Poehler
    -0.55
    émie
    -0.54
     домо
    -0.54
     Villiers
    -0.54
    POSITIVE LOGITS
    Honestly
    0.85
    Frankly
    0.85
     honestly
    0.83
     frankly
    0.82
     Honestly
    0.79
    honestly
    0.75
     disambiguazione
    0.70
     ngl
    0.69
     though
    0.66
    说实话
    0.64
    Act Density 0.131%

    No Known Activations