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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consistency or reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aso
    -0.21
    issement
    -0.16
    scribe
    -0.16
    UPI
    -0.15
    uch
    -0.15
    orman
    -0.15
    age
    -0.15
    ange
    -0.15
    undry
    -0.15
    ern
    -0.15
    POSITIVE LOGITS
    ently
    0.27
     inconsistent
    0.21
     nhau
    0.20
     across
    0.20
     throughout
    0.19
     Throughout
    0.17
    Across
    0.17
    okable
    0.17
    antly
    0.17
     Across
    0.17
    Act Density 0.022%

    No Known Activations