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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "Sh" or variations of it in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thic
    -0.19
    ecc
    -0.18
    tica
    -0.18
    evice
    -0.17
    zier
    -0.17
    jos
    -0.17
    ncia
    -0.15
    ekt
    -0.15
    ÃŁer
    -0.15
    tries
    -0.15
    POSITIVE LOGITS
    eryl
    0.32
    aron
    0.30
    awn
    0.30
    annon
    0.27
    ane
    0.25
    erry
    0.25
    aryl
    0.25
    eldon
    0.24
    eree
    0.24
    ari
    0.24
    Act Density 0.021%

    No Known Activations