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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and components related to assumptions or hypothetical scenarios

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     there
    -0.64
     the
    -0.57
     this
    -0.51
     everything
    -0.51
    ViewFeatures
    -0.47
    <eos>
    -0.47
     and
    -0.46
     e
    -0.46
     of
    -0.45
     "
    -0.43
    POSITIVE LOGITS
    الدراسه
    0.85
     Numerade
    0.80
    WebVitals
    0.74
     Tivoli
    0.74
    itudinal
    0.74
     NDEBUG
    0.74
     filial
    0.72
    tvguidetime
    0.71
     Efq
    0.71
     photolibrary
    0.71
    Act Density 0.010%

    No Known Activations