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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scriber
    -0.15
    аÑĤÑĥ
    -0.15
    chten
    -0.15
    ạc
    -0.14
    orp
    -0.14
    ignKey
    -0.14
    rams
    -0.14
    oS
    -0.14
     ë§
    -0.14
    _AMD
    -0.14
    POSITIVE LOGITS
     vo
    0.18
     prest
    0.16
     viol
    0.16
    Operating
    0.16
     ye
    0.15
    etim
    0.15
    transforms
    0.15
    'll
    0.14
    ivic
    0.14
     race
    0.14
    Act Density 0.068%

    No Known Activations