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

    Neuronpedia

    INDEX
    Explanations

    references to support and expressions of assistance or backing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fleming
    -0.76
    Hg
    -0.74
     Latimer
    -0.68
    aknya
    -0.68
     Vegas
    -0.67
     Jes
    -0.66
    JDK
    -0.66
    ريبة
    -0.66
    ✨:
    -0.66
    Vegas
    -0.65
    POSITIVE LOGITS
     support
    1.65
     supports
    1.56
     Supports
    1.54
     Support
    1.51
    Support
    1.49
    support
    1.43
     SUPPORT
    1.42
    Supports
    1.40
    supports
    1.39
     suppor
    1.38
    Act Density 0.132%

    No Known Activations