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

    Neuronpedia

    INDEX
    Explanations

    names of people or places ending in 'ran'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "ran" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earable
    -0.66
    lda
    -0.65
    £ı
    -0.65
    enne
    -0.63
    unin
    -0.62
    ensor
    -0.61
    GMT
    -0.61
    ãĢIJ
    -0.60
    ready
    -0.60
    cember
    -0.59
    POSITIVE LOGITS
    vier
    1.09
    igans
    0.90
    thus
    0.86
    igan
    0.85
    tenance
    0.85
    fo
    0.84
    ollar
    0.84
    thood
    0.83
    ormal
    0.82
    iety
    0.82
    Act Density 0.040%

    No Known Activations