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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey strong positive or negative qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oger
    -0.17
    zsche
    -0.16
    strup
    -0.15
    ırak
    -0.15
    469
    -0.15
    919
    -0.15
    ADIO
    -0.14
    èĻ«
    -0.14
    eny
    -0.14
    ERÄ°
    -0.14
    POSITIVE LOGITS
    ELL
    0.15
    imson
    0.15
    ness
    0.14
     tslib
    0.14
    _nested
    0.14
    ulo
    0.14
    ibe
    0.13
    ÅĻe
    0.13
     lap
    0.13
    robe
    0.13
    Act Density 0.232%

    No Known Activations