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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging communication or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritis
    -0.15
    umba
    -0.14
    inning
    -0.14
    native
    -0.14
    erras
    -0.13
    nob
    -0.13
    ÑĤÑĥ
    -0.13
    èĽ
    -0.13
    mpl
    -0.13
    ÙĨ
    -0.13
    POSITIVE LOGITS
    .fre
    0.18
    esine
    0.17
     freely
    0.17
     Wet
    0.14
    assen
    0.14
     ìŀIJìľł
    0.14
     use
    0.14
     any
    0.14
    652
    0.14
     anytime
    0.14
    Act Density 0.021%

    No Known Activations