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

    Neuronpedia

    INDEX
    Explanations

    references to stages or steps in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    step in, step into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vermelha
    -0.48
     fluorescent
    -0.45
     Harrington
    -0.44
     Fluorescent
    -0.43
     prolific
    -0.41
    ugc
    -0.41
     kaik
    -0.41
     μαύ
    -0.41
     onBind
    -0.40
     luzes
    -0.40
    POSITIVE LOGITS
    Step
    1.26
     Step
    1.23
     step
    1.21
     Steps
    1.17
    step
    1.16
     STEP
    1.16
    Steps
    1.15
     steps
    1.15
    STEP
    1.15
    steps
    1.09
    Act Density 0.022%

    No Known Activations