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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations or states of being

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

    following "at" indicating time or order

    np_acts-logits-general · gemini-2.0-flash

    at first, at last, at times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szóci
    -0.60
     مرئيه
    -0.55
    affine
    -0.53
    참고
    -0.50
    يكب
    -0.50
    thenia
    -0.50
    ETHING
    -0.50
    cinia
    -0.50
    MemoryWarning
    -0.50
    enterOuterAlt
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.61
     first
    0.56
    last
    0.56
    first
    0.54
    imageshack
    0.52
    tact
    0.50
     sight
    0.48
    +#+
    0.46
    listed
    0.46
    qq
    0.46
    Act Density 0.194%

    No Known Activations