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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate precise conditions or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DETECT
    -0.15
    497
    -0.15
    aud
    -0.14
    çĤī
    -0.14
    Ļ
    -0.14
    berry
    -0.14
    ERO
    -0.14
    inate
    -0.14
    .react
    -0.14
    اÙĨÙĬ
    -0.14
    POSITIVE LOGITS
    ze
    0.15
    rett
    0.15
    abox
    0.14
    .jquery
    0.14
    ilian
    0.14
    ifi
    0.14
     samo
    0.14
    styl
    0.13
    enia
    0.13
    ноз
    0.13
    Act Density 0.013%

    No Known Activations