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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or ongoing experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atre
    -0.07
    ovna
    -0.07
     Hughes
    -0.06
     Jarvis
    -0.06
    jer
    -0.06
    gs
    -0.06
    igs
    -0.06
    ationToken
    -0.06
    geme
    -0.06
     Heap
    -0.06
    POSITIVE LOGITS
    alama
    0.08
    -fw
    0.08
    illac
    0.07
    ebek
    0.07
    amam
    0.07
    ÑĢоиз
    0.07
     haven
    0.07
    okies
    0.07
     only
    0.07
    ноÑģ
    0.07
    Act Density 0.005%

    No Known Activations