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

    Neuronpedia

    INDEX
    Explanations

    sections of text that appear to be headings or titles within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.56
    ,
    -0.53
    .
    -0.53
    </i>
    -0.51
     (
    -0.50
     [
    -0.50
     o
    -0.48
     s
    -0.47
     –
    -0.47
     on
    -0.46
    POSITIVE LOGITS
     Jefus
    1.13
     pleaſure
    1.08
    tvguidetime
    1.06
     greateſt
    1.05
     Efq
    1.05
     raiſ
    1.03
     houſe
    0.99
     Theſe
    0.99
     myſelf
    0.96
    ſelf
    0.96
    Act Density 0.019%

    No Known Activations