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

    Neuronpedia

    INDEX
    Explanations

    statements about decision-making and changes in opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idebar
    -0.17
    MLS
    -0.15
    arez
    -0.15
    itorio
    -0.15
    iero
    -0.14
    μοί
    -0.14
    маÑħ
    -0.14
    .CopyTo
    -0.14
     NEGLIGENCE
    -0.14
    .syn
    -0.14
    POSITIVE LOGITS
     retract
    0.38
     resc
    0.37
     withdraw
    0.35
     withdrawn
    0.31
     reverse
    0.30
    æĴ¤
    0.30
     reversal
    0.30
     withdrawal
    0.30
     withdrew
    0.30
     change
    0.29
    Act Density 0.215%

    No Known Activations