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

    Neuronpedia

    INDEX
    Explanations

    connections and inconsistencies between actions and beliefs, particularly in the context of claims being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĤu
    -0.15
    ennis
    -0.14
     lieu
    -0.13
    celed
    -0.13
    iji
    -0.13
    utra
    -0.13
     therm
    -0.12
     Pyramid
    -0.12
    ida
    -0.12
    á»Ń
    -0.12
    POSITIVE LOGITS
     match
    0.50
     matches
    0.49
     align
    0.47
    match
    0.40
    -match
    0.38
    align
    0.38
     Align
    0.38
     matched
    0.37
     MATCH
    0.37
    matches
    0.37
    Act Density 0.526%

    No Known Activations