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

    Neuronpedia

    INDEX
    Explanations

    quotes and attributive phrases, often expressing opinions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambiguation
    -0.52
    automatically
    -0.51
    automatic
    -0.50
     automática
    -0.50
     Automatic
    -0.49
     magasiner
    -0.48
    Automatic
    -0.48
     etik
    -0.47
    ocity
    -0.47
     preventiva
    -0.47
    POSITIVE LOGITS
    NUMX
    0.91
     <<<<<<<<<<<<<<
    0.85
     “
    0.84
     “...
    0.82
    ]<<"
    0.80
     “(
    0.80
     “…
    0.78
    ，“
    0.77
    <!--[
    0.75
    ]=="
    0.72
    Act Density 0.185%

    No Known Activations