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

    Neuronpedia

    INDEX
    Explanations

    expressions and discussions surrounding judgment and critiques of actions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.59
     utafitiHapana
    -0.52
    setopt
    -0.49
     grà
    -0.47
    Steps
    -0.47
     Steps
    -0.46
    ">//
    -0.46
    뀜
    -0.46
     Hinweis
    -0.46
    featureID
    -0.45
    POSITIVE LOGITS
     judgment
    2.16
     judgement
    2.07
     judge
    2.07
     judgments
    1.93
     judging
    1.91
     judgements
    1.90
     judged
    1.88
    judge
    1.85
    judgment
    1.78
     judges
    1.77
    Act Density 0.340%

    No Known Activations