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

    Neuronpedia

    INDEX
    Explanations

    references to specific types or categories within structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.17
    اتÛĮ
    -0.15
    sdale
    -0.15
    utions
    -0.15
    iotic
    -0.15
    éĺħ读次æķ°
    -0.15
    infeld
    -0.15
    ersed
    -0.14
    ngth
    -0.14
    atics
    -0.14
    POSITIVE LOGITS
    ullivan
    0.23
    amsung
    0.22
    leep
    0.22
    ilver
    0.22
    ugar
    0.21
    pring
    0.21
    usan
    0.21
    ociety
    0.20
    outh
    0.20
    ense
    0.20
    Act Density 0.017%

    No Known Activations