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

    Neuronpedia

    INDEX
    Explanations

    words or phrases ending in 'ond'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ond" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ======
    -0.86
    ãĥ³ãĤ¸
    -0.81
    ãĤµ
    -0.80
     teasp
    -0.77
    ãĥ¼ãĥ³
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
    glers
    -0.71
    è¦ļéĨĴ
    -0.69
    jriwal
    -0.69
     è£ıç
    -0.68
    POSITIVE LOGITS
    ragon
    0.94
    ering
    0.90
    orf
    0.89
    ont
    0.85
    ond
    0.84
    rive
    0.82
    erm
    0.82
    isl
    0.82
    aire
    0.82
    rain
    0.80
    Act Density 0.008%

    No Known Activations