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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words indicating conditions or limitations in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ripp
    -0.17
    asher
    -0.14
    ozor
    -0.14
    å¨
    -0.14
     overlap
    -0.14
    076
    -0.14
    inite
    -0.13
    Insurance
    -0.13
    quals
    -0.13
    ãĥ³ãĥĨãĤ£
    -0.13
    POSITIVE LOGITS
    avour
    0.16
    ardy
    0.15
    RAP
    0.14
     perf
    0.14
    reon
    0.14
    .ribbon
    0.14
    antz
    0.14
    enas
    0.14
     rap
    0.14
    resentation
    0.14
    Act Density 0.002%

    No Known Activations