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

    Neuronpedia

    INDEX
    Explanations

    references to contrasting ideas or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evi
    -0.15
    Į¨
    -0.15
     Ïį
    -0.14
    lez
    -0.14
    INGLE
    -0.14
    adel
    -0.14
    yla
    -0.14
    .ZERO
    -0.13
    ÑĢÑĥÑĪ
    -0.13
    sel
    -0.13
    POSITIVE LOGITS
     side
    0.41
     half
    0.34
     end
    0.33
     extreme
    0.32
     party
    0.31
     direction
    0.31
    half
    0.30
    most
    0.29
     hemisphere
    0.29
    -half
    0.29
    Act Density 0.088%

    No Known Activations