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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location or context within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VICE
    -0.16
     Fuse
    -0.14
     Vice
    -0.14
    ãĥ¼ãĥŀ
    -0.14
     Kot
    -0.14
    кÑĤÑĥ
    -0.14
    uchi
    -0.14
    oron
    -0.14
    irth
    -0.13
     itself
    -0.13
    POSITIVE LOGITS
    彩
    0.15
    UU
    0.15
    corner
    0.15
    jem
    0.15
    aukee
    0.14
    canf
    0.14
    æĻ¯
    0.14
    crm
    0.14
    asje
    0.14
    мага
    0.14
    Act Density 0.574%

    No Known Activations