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

    Neuronpedia

    INDEX
    Explanations

    phrases that express contradiction or nuanced emotions regarding experiences or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Портали
    -0.38
     disambiguazione
    -0.37
    rikes
    -0.36
     cooper
    -0.34
    enterOuterAlt
    -0.34
    DIPSETTING
    -0.33
    Zunanje
    -0.33
     SimpleName
    -0.32
    Karakteristik
    -0.32
     prepar
    -0.32
    POSITIVE LOGITS
    iastes
    0.48
    styleType
    0.47
     warts
    0.47
     TextInputType
    0.46
     imperfections
    0.46
     imperfection
    0.44
     imperfect
    0.44
    ToBounds
    0.43
    ]")]
    0.43
    ThroughAttribute
    0.43
    Act Density 0.485%

    No Known Activations