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

    Neuronpedia

    INDEX
    Explanations

    citations and references from scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ura
    -0.17
    verter
    -0.17
    uch
    -0.16
     Werner
    -0.15
    amps
    -0.15
     ì§Ħ
    -0.15
    udic
    -0.14
    ì§Ħ
    -0.14
    аÑģÑĤи
    -0.14
    opy
    -0.14
    POSITIVE LOGITS
    /manual
    0.18
    rowsable
    0.16
     embarrass
    0.15
     Tess
    0.15
    äll
    0.14
    contri
    0.14
    aison
    0.14
     embarrassment
    0.14
    oose
    0.13
    exemple
    0.13
    Act Density 0.023%

    No Known Activations