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

    Neuronpedia

    INDEX
    Explanations

    sequences of ordinal language that indicate structure or order

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.18
    ToOne
    -0.16
    Fallback
    -0.15
     акÑĤи
    -0.15
    PTY
    -0.15
    å¼¾
    -0.14
    ERSIST
    -0.14
    __;↵
    -0.14
    óc
    -0.14
    าà¸ĵ
    -0.14
    POSITIVE LOGITS
     laure
    0.15
    il
    0.15
     occasionally
    0.15
    warts
    0.15
     circa
    0.14
    iling
    0.14
    तर
    0.14
    andon
    0.13
    alam
    0.13
    ifice
    0.13
    Act Density 0.039%

    No Known Activations