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

    Neuronpedia

    INDEX
    Explanations

    discussions about decision-making and changes of mind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .CopyTo
    -0.16
    MLS
    -0.15
    arez
    -0.15
    idebar
    -0.15
    illos
    -0.15
    itorio
    -0.14
    ilst
    -0.14
    μοί
    -0.14
    iero
    -0.14
    uite
    -0.14
    POSITIVE LOGITS
     retract
    0.41
     resc
    0.37
     withdraw
    0.35
    æĴ¤
    0.33
     withdrawal
    0.32
     withdrawn
    0.30
     change
    0.30
     reconsider
    0.29
     changed
    0.29
     reversal
    0.29
    Act Density 0.253%

    No Known Activations