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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking steps or progress in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weinberg
    -0.40
    ugc
    -0.40
    >
    -0.40
     vermelha
    -0.40
     Harrington
    -0.39
     konkurs
    -0.38
     amarilla
    -0.38
     Harwood
    -0.37
    ưu
    -0.36
     amarela
    -0.36
    POSITIVE LOGITS
     Step
    1.27
     step
    1.25
    Step
    1.24
     STEP
    1.24
    STEP
    1.20
    step
    1.20
     Steps
    1.14
     steps
    1.13
    Steps
    1.12
    steps
    1.05
    Act Density 0.124%

    No Known Activations