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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.19
    Ñīик
    -0.18
    edException
    -0.16
    ollo
    -0.15
    thing
    -0.14
    loo
    -0.14
    crypt
    -0.14
    tures
    -0.14
    ãĥĨãĥ«
    -0.14
    friend
    -0.14
    POSITIVE LOGITS
    ally
    0.31
    uality
    0.28
    ually
    0.23
     involving
    0.23
    als
    0.22
    ALLY
    0.21
    /inc
    0.21
    ality
    0.20
    alist
    0.19
     occurrence
    0.19
    Act Density 0.030%

    No Known Activations