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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "step" and its related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wards
    -0.20
    casts
    -0.16
    QRST
    -0.16
    ivant
    -0.16
    ect
    -0.15
    ward
    -0.15
    liner
    -0.15
     staging
    -0.15
    924
    -0.15
    ects
    -0.15
    POSITIVE LOGITS
     foot
    0.33
     aside
    0.30
    aside
    0.24
     Foot
    0.23
     FOOT
    0.23
     Aside
    0.23
     outside
    0.23
     into
    0.20
     lively
    0.20
    Aside
    0.19
    Act Density 0.014%

    No Known Activations