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

    Neuronpedia

    INDEX
    Explanations

    references to licenses or licensing-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .googleapis
    -0.16
    lient
    -0.15
    tein
    -0.15
    licant
    -0.15
    ateg
    -0.15
    ocio
    -0.14
    pag
    -0.14
    ahoma
    -0.14
    chos
    -0.14
    riba
    -0.14
    POSITIVE LOGITS
    abilities
    0.27
    ège
    0.27
    ability
    0.22
    utenant
    0.20
    udas
    0.18
    utex
    0.18
    ABILITY
    0.18
    arity
    0.17
    heap
    0.16
    ening
    0.16
    Act Density 0.017%

    No Known Activations