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

    Neuronpedia

    INDEX
    Explanations

    references to guest contributions or posts in a literary or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.63
     "...
    -0.54
     "'
    -0.52
     "[
    -0.52
     '
    -0.48
    's
    -0.47
     "(
    -0.46
     ("
    -0.45
    ..."
    -0.44
    -"
    -0.44
    POSITIVE LOGITS
     “
    0.38
    =”
    0.36
     “âĢ¦
    0.34
    –
    0.34
     (“
    0.32
     ‘
    0.32
     –
    0.32
    âĢ¦”
    0.32
     [âĢ¦]
    0.30
    –and
    0.28
    Act Density 0.188%

    No Known Activations