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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hyperlinks or references to other content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.91
     Hoh
    -0.77
    typescript
    -0.76
    dafx
    -0.76
     SRT
    -0.75
     forfait
    -0.74
    arty
    -0.74
     McDowell
    -0.73
    cabulary
    -0.73
    newState
    -0.73
    POSITIVE LOGITS
     Link
    1.79
     link
    1.77
     LINK
    1.75
     links
    1.68
    Link
    1.59
     Links
    1.57
    link
    1.55
    links
    1.53
    LINK
    1.53
     LINKS
    1.45
    Act Density 0.042%

    No Known Activations