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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presence or identification of significant entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    913
    -0.17
    nej
    -0.16
    858
    -0.16
    916
    -0.15
    owie
    -0.15
    amura
    -0.15
    hani
    -0.14
    äter
    -0.14
    secutive
    -0.14
     оÑĩ
    -0.14
    POSITIVE LOGITS
    ãĥ©ãĤ¯
    0.19
    aned
    0.16
     Bund
    0.15
    erse
    0.14
    yles
    0.14
    ẵn
    0.14
    (fetch
    0.14
    å®ħ
    0.14
    ico
    0.14
    uncio
    0.14
    Act Density 0.094%

    No Known Activations