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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a favorable viewpoint or outcome

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fasterxml
    -0.50
    PreferredItem
    -0.49
    ので
    -0.48
    ParallelGroup
    -0.48
    zeera
    -0.47
    Nich
    -0.47
    xtext
    -0.47
     vez
    -0.46
     ơn
    -0.46
     BoxDecoration
    -0.44
    POSITIVE LOGITS
     Efq
    0.81
     Theſe
    0.71
     Jefus
    0.67
     مشين
    0.67
     Mazar
    0.66
    AndEndTag
    0.66
     favourable
    0.65
     Lennox
    0.65
     *++
    0.65
     بيها
    0.65
    Act Density 0.000%

    No Known Activations