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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating choices and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VÃŃ
    -0.15
    opia
    -0.15
    rous
    -0.14
     DEALINGS
    -0.14
    lic
    -0.14
    ť
    -0.14
    aper
    -0.13
    likes
    -0.13
    osex
    -0.13
    pedia
    -0.13
    POSITIVE LOGITS
    ãĥ¬ãĥĥãĥĪ
    0.17
    ãĥģãĥ¥
    0.15
    çĮ
    0.14
    ÙħÙĦØ©
    0.14
    รà¸ģ
    0.14
    idden
    0.14
    ieren
    0.14
    633
    0.14
    elines
    0.14
     Tek
    0.14
    Act Density 0.211%

    No Known Activations