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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe compatibility or suitability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lotte
    -0.17
    ivos
    -0.17
     ARR
    -0.15
    ków
    -0.15
    /MPL
    -0.14
    tainment
    -0.14
    lÃŃÄį
    -0.14
    .LayoutStyle
    -0.14
    ccount
    -0.14
    .FontStyle
    -0.14
    POSITIVE LOGITS
     exp
    0.16
    aya
    0.16
    743
    0.14
    urt
    0.14
    etic
    0.14
     because
    0.14
    bes
    0.14
    ino
    0.14
     Mc
    0.13
     McMahon
    0.13
    Act Density 0.161%

    No Known Activations