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

    Neuronpedia

    INDEX
    Explanations

    unusual punctuation or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hta
    -0.19
    rana
    -0.17
    atura
    -0.15
    ocket
    -0.15
    ht
    -0.15
    erial
    -0.15
    epad
    -0.14
    /or
    -0.14
     Åŀah
    -0.14
    eton
    -0.14
    POSITIVE LOGITS
    greens
    0.15
    Incre
    0.14
     Uns
    0.14
    Invariant
    0.14
    tes
    0.14
    pone
    0.14
    357
    0.14
    ecies
    0.14
    rier
    0.13
    illac
    0.13
    Act Density 0.035%

    No Known Activations