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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    )|^{
    -0.63
     cherchés
    -0.63
     saites
    -0.61
    ]")]
    -0.59
     televisor
    -0.59
    NOPQRST
    -0.59
    Spoljašnje
    -0.58
    Gaz
    -0.58
    MethodImpl
    -0.57
    例句
    -0.57
    POSITIVE LOGITS
    ContentAlignment
    0.60
     Miko
    0.58
    ⓧ
    0.55
     Arrows
    0.54
     насеље
    0.52
     lagos
    0.51
    ólicos
    0.50
     Bruch
    0.50
    imbawa
    0.50
    phous
    0.49
    Act Density 0.133%

    No Known Activations