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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arten
    -0.16
    meno
    -0.14
    wh
    -0.14
    560
    -0.14
    wi
    -0.14
    aha
    -0.14
     Pap
    -0.14
    ophil
    -0.14
     Boyle
    -0.13
    imple
    -0.13
    POSITIVE LOGITS
     Wheels
    0.20
     steroids
    0.18
     wheels
    0.18
    ilere
    0.17
    /Instruction
    0.17
    еÑĢин
    0.16
    ÑģÑĤеÑĢ
    0.15
    .fb
    0.15
    еÑĢап
    0.15
    bitset
    0.14
    Act Density 0.060%

    No Known Activations