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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference checking or looking up additional information or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dy
    -0.15
     itself
    -0.14
    osy
    -0.14
    led
    -0.14
    ẩu
    -0.14
    iÄįka
    -0.14
     Dy
    -0.14
    vented
    -0.14
    arena
    -0.13
    soever
    -0.13
    POSITIVE LOGITS
     how
    0.20
     zda
    0.16
     www
    0.16
    avid
    0.16
     http
    0.16
    gili
    0.15
     latest
    0.15
    :.:
    0.15
    tah
    0.14
     https
    0.14
    Act Density 0.036%

    No Known Activations