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

    Neuronpedia

    INDEX
    Explanations

    instances of wordplay, particularly puns and other forms of linguistic creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synth
    -0.16
     upstream
    -0.15
    éĻµ
    -0.14
    arus
    -0.14
    ìĸij
    -0.14
    atar
    -0.14
    åij¨æľŁ
    -0.14
    oten
    -0.14
    ahlen
    -0.13
    ta
    -0.13
    POSITIVE LOGITS
     Turnbull
    0.18
    odyn
    0.15
    [sizeof
    0.15
    icari
    0.15
    mbH
    0.15
     animate
    0.14
     Discounts
    0.14
    igraph
    0.14
    isd
    0.14
    icator
    0.13
    Act Density 0.273%

    No Known Activations