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

    Neuronpedia

    INDEX
    Explanations

    specific positive indicators or elements in a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initComponents
    -0.73
     ker
    -0.72
    bootstrapcdn
    -0.71
    ruptcy
    -0.71
    Hawks
    -0.69
     Hawks
    -0.66
    Aca
    -0.65
    oem
    -0.64
     cas
    -0.63
    .
    -0.62
    POSITIVE LOGITS
    &+
    1.47
    >+</
    1.28
    _+
    1.22
    }+
    1.19
    ">+
    1.18
     $+\
    1.18
    }+$
    1.17
     +
    1.15
    ">'+
    1.14
    %+
    1.14
    Act Density 0.399%

    No Known Activations