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

    Neuronpedia

    INDEX
    Explanations

    references to performances or events taking place on a stage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rych
    -0.16
    ties
    -0.16
    ty
    -0.15
    amics
    -0.14
    aggio
    -0.14
    ly
    -0.14
    shake
    -0.14
     Honest
    -0.14
    thur
    -0.14
     saja
    -0.14
    POSITIVE LOGITS
    coach
    0.19
    yb
    0.16
    alam
    0.16
    LOBAL
    0.15
    yen
    0.15
    alen
    0.15
    357
    0.15
    builtin
    0.14
     Bever
    0.14
     debut
    0.14
    Act Density 0.023%

    No Known Activations