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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or capability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undi
    -0.15
    chner
    -0.15
    Nonce
    -0.15
    inia
    -0.14
    .isPresent
    -0.14
    bud
    -0.14
    Ñĥж
    -0.14
    ledon
    -0.14
    olia
    -0.14
    CEE
    -0.14
    POSITIVE LOGITS
     Carrier
    0.18
    Carrier
    0.17
    imbus
    0.17
     carrier
    0.16
    jak
    0.15
    ockey
    0.14
    hist
    0.14
    ilon
    0.14
    RSS
    0.14
    ån
    0.14
    Act Density 0.143%

    No Known Activations