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

    Neuronpedia

    INDEX
    Explanations

    patterns and relationships in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jspb
    -0.68
    NameInMap
    -0.65
    oredCriteria
    -0.65
    цездатний
    -0.59
    évaluateur
    -0.58
     Roskov
    -0.54
     SafeMath
    -0.54
     invokingState
    -0.54
    rrggbb
    -0.53
    Aholisi
    -0.53
    POSITIVE LOGITS
    RUnlock
    0.74
     second
    0.62
     השני
    0.59
    jsdelivr
    0.56
    AttributeSet
    0.55
    second
    0.55
     ikinci
    0.54
    nikami
    0.54
    istoitu
    0.53
     SECOND
    0.53
    Act Density 1.248%

    No Known Activations