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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating structure or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignet
    -0.15
    дж
    -0.15
     Till
    -0.14
    afone
    -0.14
    bum
    -0.14
     thereby
    -0.14
    jong
    -0.14
    bable
    -0.13
    irit
    -0.13
     thus
    -0.13
    POSITIVE LOGITS
    oret
    0.17
    -valu
    0.14
    odos
    0.14
    illard
    0.13
    orem
    0.13
    InThe
    0.13
    ugas
    0.13
    loys
    0.13
    )((((
    0.13
    ither
    0.12
    Act Density 0.128%

    No Known Activations