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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "name" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rego
    -0.18
    tica
    -0.16
    ln
    -0.15
    anus
    -0.15
    nds
    -0.15
    inae
    -0.15
    ëĭ¤ëĬĶ
    -0.15
    roy
    -0.15
    neath
    -0.15
    iano
    -0.15
    POSITIVE LOGITS
    ake
    0.33
    plate
    0.32
    plates
    0.29
    paced
    0.25
    cheap
    0.24
    less
    0.23
    Surname
    0.23
    åı¤å±ĭ
    0.22
    ervers
    0.22
    AKE
    0.22
    Act Density 0.119%

    No Known Activations