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

    Neuronpedia

    INDEX
    Explanations

    words related to famous names or public figures

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letter 'G' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.84
    ĪĴ
    -0.80
    ĸļ
    -0.79
    ACTED
    -0.71
     scrut
    -0.68
     enactment
    -0.68
     rupture
    -0.67
     exception
    -0.64
     flank
    -0.63
     consistency
    -0.62
    POSITIVE LOGITS
    ierrez
    0.95
    ppe
    0.86
    onz
    0.85
    raltar
    0.85
    reau
    0.84
    apon
    0.82
    espie
    0.82
    veland
    0.81
    grain
    0.81
    apons
    0.81
    Act Density 0.123%

    No Known Activations