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

    Neuronpedia

    INDEX
    Explanations

    instances of words indicating types of organisms or species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zem
    -0.16
    cts
    -0.15
    ontent
    -0.15
    edn
    -0.14
     mı
    -0.14
    ommen
    -0.14
    hdr
    -0.14
    gii
    -0.14
    ACT
    -0.13
    Ñĸв
    -0.13
    POSITIVE LOGITS
    affer
    0.15
    <dim
    0.15
    å±ĭ
    0.15
    orca
    0.14
    665
    0.14
    eff
    0.14
    ourg
    0.14
     fist
    0.14
    igan
    0.14
    ensed
    0.13
    Act Density 0.003%

    No Known Activations