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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the substring "som" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppers
    -0.15
    eous
    -0.15
    हन
    -0.15
    _hold
    -0.15
    uring
    -0.15
    è§Ī
    -0.15
    loyd
    -0.14
    OUGH
    -0.14
    ux
    -0.14
    çĴ
    -0.14
    POSITIVE LOGITS
    brero
    0.36
    ewhere
    0.36
    ewhat
    0.35
    etime
    0.33
    erville
    0.32
    mers
    0.30
    erset
    0.29
    eday
    0.29
    mel
    0.27
    thing
    0.26
    Act Density 0.009%

    No Known Activations