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

    Neuronpedia

    INDEX
    Explanations

    prompts or invitations for feedback or comments

    oai_token-act-pair · gpt-3.5-turbo

    references to audience interaction and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consum
    -0.66
    ccording
    -0.64
    rpm
    -0.60
     Canaveral
    -0.59
     funer
    -0.59
     physic
    -0.58
     Orig
    -0.57
    olid
    -0.56
     rescue
    -0.56
     simul
    -0.56
    POSITIVE LOGITS
     below
    1.00
     section
    0.95
    below
    0.91
     sections
    0.78
     comments
    0.74
     pane
    0.71
    ariat
    0.71
     BELOW
    0.71
    section
    0.69
     SECTION
    0.69
    Act Density 0.043%

    No Known Activations