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

    Neuronpedia

    INDEX
    Explanations

    instructional phrases about creating and sharing content or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ½
    -0.15
    aptor
    -0.15
    udad
    -0.15
    vod
    -0.14
     proc
    -0.14
    iaux
    -0.14
    ulos
    -0.14
     picking
    -0.14
     Grab
    -0.14
    .Generation
    -0.13
    POSITIVE LOGITS
     then
    0.23
     passed
    0.23
     sell
    0.22
    then
    0.21
     sharing
    0.21
    åĪĨ享
    0.21
     send
    0.21
     share
    0.21
     shared
    0.21
     distribute
    0.20
    Act Density 0.419%

    No Known Activations