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

    Neuronpedia

    INDEX
    Explanations

    specific tags and labels related to categorization and differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alanta
    -0.59
    nadequate
    -0.56
    Fprintf
    -0.55
    hdashline
    -0.54
     sledge
    -0.53
    forgotten
    -0.52
    brainly
    -0.52
     Quid
    -0.52
     Thesaurus
    -0.52
    ORETICAL
    -0.51
    POSITIVE LOGITS
     whether
    0.73
     distinguish
    0.73
     distinguir
    0.65
     epoca
    0.64
     classify
    0.62
     WHETHER
    0.61
    whether
    0.61
    oa̍t
    0.60
     ErrIntOverflow
    0.57
     وصلة
    0.57
    Act Density 0.702%

    No Known Activations