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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¨
    -0.16
    ecta
    -0.16
     tid
    -0.16
     bou
    -0.15
    strt
    -0.14
    ipple
    -0.14
    ntag
    -0.14
    jes
    -0.14
    rtl
    -0.14
    enna
    -0.14
    POSITIVE LOGITS
     Steph
    0.19
    -step
    0.19
    step
    0.19
     step
    0.18
    .step
    0.18
     Step
    0.18
     stepped
    0.17
     FOOT
    0.17
     toes
    0.16
     stepping
    0.16
    Act Density 0.022%

    No Known Activations