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

    Neuronpedia

    INDEX
    Explanations

    references to official statements or documentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥĥãĤ¯
    -0.19
    apollo
    -0.16
    allah
    -0.15
    éŁ
    -0.15
    mand
    -0.15
    arters
    -0.15
    annon
    -0.14
     sobie
    -0.14
    AFF
    -0.14
     Neutral
    -0.13
    POSITIVE LOGITS
    iyan
    0.16
    egl
    0.14
    istine
    0.14
     Latter
    0.14
    ioni
    0.14
    Ħ
    0.14
     FRIEND
    0.14
    @student
    0.13
    pNet
    0.13
     Cave
    0.13
    Act Density 0.056%

    No Known Activations