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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a past context or events related to agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.19
    assin
    -0.17
    rien
    -0.15
    869
    -0.15
    æķħ
    -0.15
    ãĥ³ãĥĢ
    -0.15
    nicos
    -0.14
    ãĥ³ãĥĹ
    -0.14
    _mC
    -0.14
    315
    -0.14
    POSITIVE LOGITS
    als
    0.15
    umann
    0.15
     ins
    0.15
    ins
    0.15
    iei
    0.14
    گاÙĨÛĮ
    0.14
     Tight
    0.14
    ÑĩÑĥк
    0.14
     Worm
    0.14
     Tune
    0.13
    Act Density 0.008%

    No Known Activations