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

    Neuronpedia

    INDEX
    Explanations

    instructions or references to sequential actions or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.65
     CURIAM
    -0.65
    tanleria
    -0.63
     LEYENDO
    -0.59
    CreateMap
    -0.57
    URLException
    -0.54
    clable
    -0.54
    Argumento
    -0.53
     Bastian
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
     step
    1.91
     steps
    1.82
    Step
    1.68
     Step
    1.66
    step
    1.65
     Steps
    1.64
    steps
    1.56
    Steps
    1.49
     stepped
    1.43
     STEPS
    1.39
    Act Density 0.139%

    No Known Activations