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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition or movement towards a destination or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    need
    -0.15
    iller
    -0.15
    æķ·
    -0.14
    à¤ľà¤¨
    -0.14
    inya
    -0.14
    |int
    -0.14
    uts
    -0.14
    agu
    -0.13
    .cert
    -0.13
    èĬĿ
    -0.13
    POSITIVE LOGITS
    /out
    0.20
    prising
    0.17
    abajo
    0.16
     an
    0.15
    (
    0.14
    /from
    0.14
     a
    0.14
     nu
    0.14
    eing
    0.14
     un
    0.14
    Act Density 0.098%

    No Known Activations