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

    Neuronpedia

    INDEX
    Explanations

    technical or technological outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fing
    -0.86
    ifications
    -0.86
    ifying
    -0.76
    ification
    -0.76
    tics
    -0.73
    bones
    -0.73
    IFIC
    -0.70
    enger
    -0.68
    bor
    -0.68
    stra
    -0.68
    POSITIVE LOGITS
    aneous
    0.70
    INAL
    0.69
    ãĤ¼ãĤ¦ãĤ¹
    0.69
    ames
    0.69
    ãĤ´ãĥ³
    0.67
     pandemonium
    0.66
    ivil
    0.66
     conflic
    0.65
     resultant
    0.65
    uez
    0.64
    Act Density 0.027%

    No Known Activations