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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stuff
    -0.16
    use
    -0.15
     stuff
    -0.15
    ijo
    -0.15
    417
    -0.15
    flows
    -0.15
    igram
    -0.14
    259
    -0.14
     Stuff
    -0.14
    bard
    -0.14
    POSITIVE LOGITS
    ï¸ı
    0.31
    ãģ¤ãģ®
    0.19
     different
    0.18
    ãĥ¶
    0.18
    -legged
    0.16
     tiers
    0.16
    -Ñħ
    0.16
    ½
    0.15
    _locator
    0.15
    .scalablytyped
    0.15
    Act Density 0.281%

    No Known Activations