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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plus
    -0.45
     +
    -0.42
     Plus
    -0.38
     PLUS
    -0.36
     minus
    -0.33
     плÑİ
    -0.31
    plus
    -0.30
    Plus
    -0.30
    -plus
    -0.28
    _plus
    -0.27
    POSITIVE LOGITS
     together
    0.26
     Together
    0.26
    Together
    0.25
    ä¸Ģèµ·
    0.21
    gether
    0.20
    +");↵
    0.18
     вмеÑģÑĤе
    0.18
     zusammen
    0.17
    +Sans
    0.17
     birlikte
    0.17
    Act Density 0.097%

    No Known Activations