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

    Neuronpedia

    INDEX
    Explanations

    numerical values and patterns related to digital signals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.84
     resourceCulture
    -0.82
    -0.79
     Majefty
    -0.79
    IntoConstraints
    -0.74
     Monfieur
    -0.74
     purpoſe
    -0.72
     Houſe
    -0.71
     poffe
    -0.70
    tagHelperRunner
    -0.69
    POSITIVE LOGITS
     for
    0.47
    的她
    0.46
     inter
    0.45
    dijk
    0.45
    granate
    0.45
     He
    0.45
     N
    0.43
    bní
    0.43
     cor
    0.43
     local
    0.43
    Act Density 0.036%

    No Known Activations