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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hopefully
    -0.14
     mÃł
    -0.14
    opo
    -0.13
    ullo
    -0.13
     *)
    -0.13
    _almost
    -0.13
    Ñıгом
    -0.13
    ince
    -0.13
    ãģ»
    -0.13
    åİŁæĿ¥
    -0.12
    POSITIVE LOGITS
     however
    1.05
     though
    0.95
    however
    0.75
    though
    0.71
     Though
    0.68
     jedoch
    0.65
    Though
    0.65
     However
    0.64
     HOWEVER
    0.63
     allerdings
    0.57
    Act Density 1.177%

    No Known Activations