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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "On" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.23
    quired
    -0.19
    rosse
    -0.16
    gos
    -0.16
    quir
    -0.16
    eb
    -0.16
    g
    -0.15
    erer
    -0.15
    eur
    -0.14
    ÑĥлÑĮ
    -0.14
    POSITIVE LOGITS
    ward
    0.27
    assis
    0.26
    ions
    0.25
    iones
    0.22
    WARD
    0.22
    ion
    0.22
    egin
    0.21
    slaught
    0.20
    ancock
    0.20
    stage
    0.19
    Act Density 0.033%

    No Known Activations