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

    Neuronpedia

    INDEX
    Explanations

    hashtags or similar symbols indicating categories or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.16
     Canter
    -0.15
    arov
    -0.15
    867
    -0.15
    viso
    -0.14
    deen
    -0.14
    arsing
    -0.14
    _CUDA
    -0.14
    č↵č↵č↵č↵
    -0.14
    eree
    -0.14
    POSITIVE LOGITS
    avin
    0.16
    amenti
    0.15
    zel
    0.15
    ief
    0.15
     Branch
    0.14
     pseud
    0.14
    ennon
    0.14
    ahy
    0.14
     Chess
    0.14
    urr
    0.13
    Act Density 0.000%

    No Known Activations