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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions, thresholds, or caution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.36
     especiales
    -0.34
    oneofs
    -0.34
    følgelig
    -0.32
    adona
    -0.32
     carnet
    -0.31
     klart
    -0.31
     universitaria
    -0.30
    正好
    -0.30
     Urbano
    -0.30
    POSITIVE LOGITS
     slightest
    0.88
     tiny
    0.66
     moindre
    0.63
    mybatisplus
    0.63
    iniest
    0.61
    ほん
    0.60
     ANY
    0.59
     slight
    0.59
    ちょっとした
    0.59
     Slight
    0.58
    Act Density 0.330%

    No Known Activations