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

    Neuronpedia

    INDEX
    Explanations

    the word "Here" in various contexts and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    óng
    -0.16
    оÑģÑĤав
    -0.15
    ipel
    -0.15
    ottie
    -0.14
    õ
    -0.14
    ominated
    -0.14
    ounded
    -0.14
     Ved
    -0.14
    ég
    -0.14
    енÑĮ
    -0.13
    POSITIVE LOGITS
    ford
    0.27
    after
    0.20
    ina
    0.19
     lies
    0.19
     Comes
    0.18
     lie
    0.17
     comes
    0.17
     Come
    0.17
    olid
    0.17
     are
    0.16
    Act Density 0.026%

    No Known Activations