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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the action of explaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.72
     Normdatei
    -0.66
    RetentionPolicy
    -0.61
     usize
    -0.60
    XmlAccessorType
    -0.59
     Tief
    -0.58
    AsUp
    -0.58
     interesses
    -0.53
    fficking
    -0.53
     commerciaux
    -0.52
    POSITIVE LOGITS
     explanation
    3.75
     explain
    3.70
     explanations
    3.46
     explaining
    3.35
    explain
    3.23
     Explain
    3.12
     explained
    3.10
    explanation
    3.09
     explains
    3.04
     Explanation
    2.94
    Act Density 0.077%

    No Known Activations