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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing doubt or opposition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.96
    isode
    -0.75
    ĸļ
    -0.75
    cffff
    -0.74
     Dragonbound
    -0.74
    ESE
    -0.74
    Located
    -0.74
    ]).
    -0.73
    reated
    -0.72
    ļéĨĴ
    -0.72
    POSITIVE LOGITS
     occasional
    1.31
     some
    1.15
     occasionally
    1.04
     sometimes
    1.01
     exceptions
    0.91
     faults
    0.90
     SOME
    0.90
     detractors
    0.89
    some
    0.88
     inconven
    0.85
    Act Density 0.423%

    No Known Activations