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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and expressions of satisfaction in reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DECREF
    -0.15
    NES
    -0.14
    ertest
    -0.14
    dle
    -0.14
    dll
    -0.14
     Moses
    -0.14
    iens
    -0.14
    еÑģÑĤв
    -0.13
     Nickel
    -0.13
    ÑĢабаÑĤ
    -0.13
    POSITIVE LOGITS
    hev
    0.18
    urtle
    0.17
     Afr
    0.15
    ird
    0.15
    ÑĥÑĢÑĥ
    0.15
    ya
    0.14
    compact
    0.14
     compliments
    0.14
    itsu
    0.14
    obb
    0.14
    Act Density 0.047%

    No Known Activations