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

    Neuronpedia

    INDEX
    Explanations

    phrases involving conjunctions that indicate a connection or relation between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otta
    -0.17
    nip
    -0.16
    éľĢ
    -0.15
    asers
    -0.15
    بع
    -0.14
    lox
    -0.14
     Bek
    -0.14
    aises
    -0.13
    ils
    -0.13
    zin
    -0.13
    POSITIVE LOGITS
    xr
    0.17
    ãģĹãĤĩãģĨ
    0.14
    uju
    0.14
    reed
    0.14
    bl
    0.14
    learn
    0.14
    od
    0.13
    bjerg
    0.13
    TEGER
    0.13
     thereby
    0.13
    Act Density 0.223%

    No Known Activations