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

    Neuronpedia

    INDEX
    Explanations

    patterns and variables within mathematical or statistical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquity
    -1.59
    igu
    -1.51
    oring
    -1.49
    olo
    -1.45
    *"
    -1.44
    ozo
    -1.43
    igen
    -1.42
    amycin
    -1.41
    aments
    -1.40
    ongo
    -1.39
    POSITIVE LOGITS
    ģ
    1.72
    ®
    1.70
    ĻĤ
    1.67
    «
    1.63
      ↵
    1.48
    ↵↵
    1.48
    č↵č↵
    1.48
    1.48
    1.48
    ↵
    1.48
    Act Density 0.049%

    No Known Activations