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

    Neuronpedia

    INDEX
    Explanations

    multi-step processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a step-by-step process or methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ribbon
    -0.70
     persuasive
    -0.69
     peac
    -0.69
     velvet
    -0.68
     fuss
    -0.68
     cush
    -0.68
     disposable
    -0.68
     burnt
    -0.67
     multit
    -0.67
     canned
    -0.67
    POSITIVE LOGITS
    step
    1.32
    DragonMagazine
    1.14
    steps
    0.99
    Step
    0.99
    daughter
    0.89
    STEP
    0.88
    hens
    0.87
    Mania
    0.82
    iblings
    0.81
    dad
    0.81
    Act Density 0.004%

    No Known Activations