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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hek
    -0.15
    esen
    -0.15
    ouri
    -0.15
     Mona
    -0.15
    nda
    -0.15
    ordan
    -0.14
    obra
    -0.14
     ÑĢÑĥкÑĥ
    -0.14
    alf
    -0.14
    oba
    -0.13
    POSITIVE LOGITS
    ÑģÑĮ
    0.16
    #ac
    0.16
    qli
    0.15
    #__
    0.15
    vic
    0.14
    ilio
    0.14
    PickerController
    0.14
    brero
    0.14
    ugg
    0.13
    athers
    0.13
    Act Density 0.183%

    No Known Activations