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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific items, behaviors, or attributes that can indicate personal interests or physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ible
    -0.16
     Mall
    -0.15
    ers
    -0.14
    ings
    -0.14
    enor
    -0.14
    avi
    -0.14
    oppers
    -0.14
    isser
    -0.14
    vider
    -0.14
    htar
    -0.14
    POSITIVE LOGITS
    kili
    0.16
     içeren
    0.15
    ophobic
    0.15
    rio
    0.15
    -bearing
    0.14
    fragistics
    0.14
    ATAB
    0.14
    kla
    0.14
    .RunWith
    0.14
    Truthy
    0.14
    Act Density 0.051%

    No Known Activations