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

    Neuronpedia

    INDEX
    Explanations

    references to shared information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azon
    -0.17
    oken
    -0.15
    ÑĢави
    -0.15
    olk
    -0.15
     Brit
    -0.14
    apesh
    -0.13
    жд
    -0.13
     Milf
    -0.13
    erra
    -0.13
    ħ§
    -0.13
    POSITIVE LOGITS
     tonight
    0.24
     myself
    0.23
     here
    0.21
     below
    0.19
     today
    0.18
     ÙĩÙĨا
    0.17
     hoping
    0.17
     because
    0.17
     hopefully
    0.17
     hopes
    0.16
    Act Density 0.183%

    No Known Activations