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

    Neuronpedia

    INDEX
    Explanations

    references to religious figures and their messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yans
    -0.15
    igure
    -0.15
     incididunt
    -0.14
     mythical
    -0.14
     infect
    -0.13
    osal
    -0.13
     myth
    -0.13
     turb
    -0.13
     scattering
    -0.13
    Pitch
    -0.13
    POSITIVE LOGITS
     visions
    0.29
    visions
    0.22
     experiences
    0.19
     channel
    0.18
     revelations
    0.18
     appar
    0.17
     vision
    0.17
     visionary
    0.17
     Channel
    0.16
     messages
    0.16
    Act Density 0.175%

    No Known Activations