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

    Neuronpedia

    INDEX
    Explanations

    words related to the process of formulating or manipulating something

    oai_token-act-pair · gpt-3.5-turbo

    words related to formulation or structuring concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aghan
    -0.81
    rip
    -0.78
    andra
    -0.71
    ening
    -0.70
    lest
    -0.69
    Corp
    -0.68
    apache
    -0.68
    edit
    -0.67
    eyed
    -0.65
    cil
    -0.65
    POSITIVE LOGITS
    ulate
    1.14
    ulating
    0.90
    ulates
    0.86
    ulators
    0.84
    ulator
    0.78
    ulated
    0.77
    oidal
    0.77
    urally
    0.75
    ulation
    0.74
     CTR
    0.74
    Act Density 0.066%

    No Known Activations