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

    Neuronpedia

    INDEX
    Explanations

    indications of emotional context or expressing disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.96
     chi̍t
    -0.92
    <bos>
    -0.80
    Portail
    -0.79
    Geplaatst
    -0.79
     '',
    -0.78
    addCriterion
    -0.76
    PreferredItem
    -0.76
    :✨
    -0.74
    页面存档备份
    -0.73
    POSITIVE LOGITS
    .
    1.06
     thereby
    0.64
     näin
    0.54
    Moreover
    0.53
     accordingly
    0.53
     Moreover
    0.53
     respectivamente
    0.52
    Plus
    0.52
    ↵↵
    0.51
     Additionally
    0.51
    Act Density 0.848%

    No Known Activations