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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.15
    jin
    -0.14
    ovo
    -0.14
     Shame
    -0.14
    tap
    -0.14
    kad
    -0.14
    hip
    -0.14
     this
    -0.14
    rine
    -0.14
    onical
    -0.14
    POSITIVE LOGITS
    /th
    0.23
    zelf
    0.19
    /her
    0.19
     particular
    0.15
     latter
    0.15
     же
    0.15
    _registro
    0.15
    ìłĢ
    0.14
    à¹ģหล
    0.14
    curity
    0.14
    Act Density 0.445%

    No Known Activations