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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.96
     myſelf
    -0.92
     Jefus
    -0.88
     himſelf
    -0.88
     quæ
    -0.88
     Efq
    -0.85
     Majefty
    -0.85
    Autoritní
    -0.84
    ſelf
    -0.84
     étoient
    -0.81
    POSITIVE LOGITS
     Maybe
    1.19
    Maybe
    1.17
     maybe
    1.11
     Perhaps
    1.06
    maybe
    1.06
     perhaps
    1.00
    Perhaps
    0.98
    perhaps
    0.91
     Vielleicht
    0.88
    Vielleicht
    0.82
    Act Density 0.120%

    No Known Activations