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

    Neuronpedia

    INDEX
    Explanations

    notification markers or indicators typical in coding or data structure contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.94
    NUMX
    -0.93
     ་་
    -0.91
    ContentAlignment
    -0.89
    culously
    -0.88
     doubtnut
    -0.87
     ―――――
    -0.87
     Efq
    -0.85
     coö
    -0.84
    olesale
    -0.84
    POSITIVE LOGITS
    <eos>
    0.91
    UnusedPrivate
    0.62
     diatas
    0.59
    !!!
    0.58
    ↵
    0.58
      
    0.57
    "
    0.56
     ontem
    0.55
    ".
    0.53
    esinde
    0.53
    Act Density 0.136%

    No Known Activations