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

    Neuronpedia

    INDEX
    Explanations

    references to performances or events with notable metrics or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.82
    Dick
    -0.71
    ptin
    -0.70
    ILA
    -0.66
     Answers
    -0.66
     fixme
    -0.65
     CLSID
    -0.65
    harm
    -0.64
    hig
    -0.63
    cffffcc
    -0.62
    POSITIVE LOGITS
    ノ
    0.70
    �
    0.69
     EDITION
    0.67
     standpoint
    0.67
    aks
    0.66
    �
    0.65
     date
    0.64
    ward
    0.63
    hof
    0.62
     divergence
    0.62
    Act Density 1.474%

    No Known Activations