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

    Neuronpedia

    INDEX
    Explanations

    HTML elements or attributes related to parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.66
    :✨
    -0.52
    vi
    -0.51
    ci
    -0.51
    ,
    -0.47
    +
    -0.47
     and
    -0.46
    est
    -0.46
    :
    -0.46
     represent
    -0.46
    POSITIVE LOGITS
     étoient
    0.84
     Theſe
    0.81
     auroit
    0.80
     avoient
    0.78
     feroit
    0.75
     étoit
    0.74
     itſelf
    0.74
    OGND
    0.73
     IBRARY
    0.72
    ENEFITS
    0.72
    Act Density 0.276%

    No Known Activations