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

    Neuronpedia

    INDEX
    Explanations

    terms related to providing detailed explanations or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADL
    -0.50
    asser
    -0.46
    CASS
    -0.45
    assis
    -0.42
    /**
    -0.42
     cast
    -0.42
    ASL
    -0.39
    CSM
    -0.39
     ADF
    -0.38
    CAS
    -0.38
    POSITIVE LOGITS
     explanation
    0.66
     explicación
    0.60
    explanation
    0.59
    gebob
    0.58
     explains
    0.58
    UnknownFieldSet
    0.57
    haustible
    0.57
     explaining
    0.56
    explanatory
    0.54
     purpoſe
    0.53
    Act Density 0.288%

    No Known Activations