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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating high expectations or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _EVAL
    -0.17
    ITIZE
    -0.17
     Beacon
    -0.16
    urgeon
    -0.16
    elo
    -0.16
    ilo
    -0.15
    ardi
    -0.14
     Bullet
    -0.14
    æĶ¶
    -0.14
    èĪŀ
    -0.14
    POSITIVE LOGITS
    éĻ°
    0.17
     umb
    0.16
    umblr
    0.15
    ÑĢавилÑĮ
    0.15
    kov
    0.14
    /static
    0.14
    ©
    0.14
    obbled
    0.14
    UID
    0.14
    .IContainer
    0.13
    Act Density 0.009%

    No Known Activations