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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate announcements or declarations about significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anker
    -0.17
    ãĥ¼ãĤ¸
    -0.16
    é¤
    -0.14
    mol
    -0.14
    acob
    -0.14
    å§Ĩ
    -0.14
    919
    -0.14
    //{{
    -0.14
     eens
    -0.14
    862
    -0.13
    POSITIVE LOGITS
    otion
    0.17
     manip
    0.15
    ãĥ¼ãĥĨ
    0.15
    oo
    0.14
    æ¬
    0.14
    éĤ¦
    0.14
     tempor
    0.14
    gest
    0.14
    ?=.*
    0.14
    ook
    0.14
    Act Density 0.058%

    No Known Activations