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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing hypothetical situations and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auf
    -0.15
     their
    -0.15
    asma
    -0.15
     stret
    -0.14
    αι
    -0.14
    iaz
    -0.14
    æ¦
    -0.14
    ноÑģи
    -0.14
    achine
    -0.14
    AEA
    -0.14
    POSITIVE LOGITS
    Wunused
    0.17
     Schl
    0.16
    ÑģилÑĮ
    0.15
    gel
    0.15
    rana
    0.15
     own
    0.14
    own
    0.14
    pread
    0.14
    .tbl
    0.13
     programm
    0.13
    Act Density 0.248%

    No Known Activations