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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiry phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.67
    niająca
    -0.48
    whatever
    -0.47
    tagHelper
    -0.46
    CrossRef
    -0.46
    Personendaten
    -0.46
    chosen
    -0.44
     whatever
    -0.44
     whichever
    -0.43
    NameInMap
    -0.42
    POSITIVE LOGITS
     are
    0.82
     role
    0.77
     kinds
    0.75
     sort
    0.75
     effect
    0.75
     sorts
    0.75
     kind
    0.74
     steps
    0.74
     aspects
    0.70
     factors
    0.69
    Act Density 0.228%

    No Known Activations