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

    Neuronpedia

    INDEX
    Explanations

    instances of communication and expressions of thought or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctx
    -0.16
    abr
    -0.15
    ãģıãĤī
    -0.14
    imax
    -0.14
    ctxt
    -0.14
     longitud
    -0.14
     jit
    -0.13
    pton
    -0.13
    .med
    -0.13
     Nah
    -0.13
    POSITIVE LOGITS
    sian
    0.16
    nds
    0.15
     é¹
    0.15
    057
    0.15
    hue
    0.14
    ernal
    0.14
    unos
    0.14
    ados
    0.14
    oud
    0.14
    é¹
    0.14
    Act Density 2.862%

    No Known Activations