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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hol
    -0.17
    sed
    -0.16
    doch
    -0.16
    ÏĨÏħ
    -0.16
    eden
    -0.15
    htdocs
    -0.15
    hus
    -0.15
    hope
    -0.15
    меÑī
    -0.15
    izes
    -0.15
    POSITIVE LOGITS
    ting
    0.17
    uppy
    0.16
    fork
    0.16
    TING
    0.16
    iard
    0.15
    rek
    0.15
    INGER
    0.15
    zsche
    0.15
    ãĥ«ãĥī
    0.15
    antor
    0.15
    Act Density 0.021%

    No Known Activations