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

    Neuronpedia

    INDEX
    Explanations

    instances of indirect reference to people or objects through context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spm
    -0.17
    orean
    -0.16
    bench
    -0.15
    OMPI
    -0.15
    _busy
    -0.14
     saÄŁlay
    -0.14
    icÃŃ
    -0.14
     gì
    -0.13
    ãĥªãĤ¢
    -0.13
    ymous
    -0.13
    POSITIVE LOGITS
    apper
    0.18
    assen
    0.15
    aise
    0.15
    é¦
    0.14
    enser
    0.14
    inci
    0.14
    oi
    0.14
    pector
    0.14
    ycz
    0.14
     liner
    0.14
    Act Density 0.200%

    No Known Activations