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

    Neuronpedia

    INDEX
    Explanations

    terms related to unusual or abnormal situations or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliz
    -0.15
    pherical
    -0.14
    eil
    -0.14
    hores
    -0.13
    ombo
    -0.13
    IRCLE
    -0.13
    opleft
    -0.13
    oltip
    -0.13
    eros
    -0.13
    illery
    -0.13
    POSITIVE LOGITS
    LY
    0.17
     Morm
    0.17
    linger
    0.17
    ify
    0.17
    ly
    0.16
    à¸Ľà¸£à¸°à¸Īำ
    0.16
     Levine
    0.15
    ely
    0.15
    ifier
    0.15
    owie
    0.14
    Act Density 0.020%

    No Known Activations