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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "base."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.22
    ship
    -0.21
    sp
    -0.19
    smith
    -0.19
    sm
    -0.18
    reich
    -0.17
    Ø©
    -0.17
    sdale
    -0.17
    sla
    -0.16
    ness
    -0.16
    POSITIVE LOGITS
    camp
    0.21
    band
    0.20
    born
    0.19
    cover
    0.17
    coat
    0.17
     hạ
    0.16
    -ÑĤо
    0.16
    paring
    0.16
    istrovstvÃŃ
    0.16
    gfx
    0.15
    Act Density 0.040%

    No Known Activations