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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical symbols or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Avery
    -0.51
    caler
    -0.49
    principalTable
    -0.47
    Avery
    -0.45
     Carleton
    -0.44
    NameInMap
    -0.42
    glGen
    -0.42
     dụ
    -0.41
    нець
    -0.41
     Gregor
    -0.41
    POSITIVE LOGITS
    SH
    0.93
    ASH
    0.92
     SH
    0.91
     ASH
    0.88
    ash
    0.85
    sh
    0.85
    alsh
    0.83
     ash
    0.81
     PHA
    0.80
    Sh
    0.79
    Act Density 0.505%

    No Known Activations