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

    Neuronpedia

    INDEX
    Explanations

    terms related to formulation or manipulation, such as "formulating", "manipulating", and "insulating"

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of formulating or structuring ideas and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rip
    -0.81
    aghan
    -0.74
    Corp
    -0.70
    andra
    -0.68
    Stew
    -0.66
     Angels
    -0.65
    Bone
    -0.64
    apache
    -0.64
    Chain
    -0.63
    Crew
    -0.63
    POSITIVE LOGITS
    ulate
    1.25
    ulating
    1.06
    ulators
    0.98
    ulates
    0.98
    ulator
    0.93
    ulation
    0.92
    ulated
    0.88
    oidal
    0.80
     CTR
    0.79
    ulatory
    0.77
    Act Density 0.055%

    No Known Activations