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

    Neuronpedia

    INDEX
    Explanations

    mentions of new additions, updates, or features in technology contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to new features or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.81
    SPONSORED
    -0.80
    OPA
    -0.79
    itta
    -0.76
    mination
    -0.72
    osure
    -0.72
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.71
    cius
    -0.71
    agree
    -0.71
    mop
    -0.69
    POSITIVE LOGITS
    bies
    1.27
    bie
    1.25
     arrivals
    1.09
     additions
    1.04
    foundland
    0.92
     batch
    0.85
     edition
    0.84
     addition
    0.83
    iating
    0.83
     flagship
    0.78
    Act Density 0.092%

    No Known Activations