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

    Neuronpedia

    INDEX
    Explanations

    informal expressions and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and numerical values within text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     estekak
    -0.53
    zzleHttp
    -0.51
     المعيارى
    -0.48
    ///</
    -0.42
    !*\
    -0.41
     referenties
    -0.39
     Italijani
    -0.36
     ""],
    -0.36
    ьаж
    -0.34
    󠁴
    -0.34
    POSITIVE LOGITS
    side
    0.49
    UniformLocation
    0.49
    seits
    0.48
     behalf
    0.48
    MLLoader
    0.47
    fast
    0.47
    び
    0.47
    omis
    0.46
    inat
    0.46
    hacia
    0.46
    Act Density 0.161%

    No Known Activations