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

    Neuronpedia

    INDEX
    Explanations

    references to popular media and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ->__
    -0.17
    ĵåIJį
    -0.16
    itsu
    -0.15
    ãĤµãĤ¤
    -0.15
    unde
    -0.15
     åIJī
    -0.14
    lil
    -0.14
     Rabbit
    -0.14
    /pm
    -0.14
     Lav
    -0.14
    POSITIVE LOGITS
     Indy
    0.40
     Indiana
    0.38
    Indiana
    0.34
     Jones
    0.28
     Raiders
    0.27
    Jones
    0.25
     Indianapolis
    0.25
    indy
    0.25
     Harrison
    0.24
     Marion
    0.24
    Act Density 0.015%

    No Known Activations