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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and references to evidence or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.69
     "
    -0.54
     (
    -0.54
    .
    -0.52
    ;
    -0.51
    :
    -0.51
    newArrayList
    -0.50
     “
    -0.50
    ...
    -0.47
    ].
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.83
    WaitGroup
    0.81
    SourceChecksum
    0.78
    +#+#
    0.76
     Signalez
    0.75
     незавершена
    0.72
     MyBatis
    0.72
     admittedly
    0.70
     nahilalakip
    0.69
    Rhestr
    0.68
    Act Density 0.342%

    No Known Activations