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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and procedures like web forms, portals, technicalities, and electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bureaucratic processes and official documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.63
    esides
    -0.59
     deadliest
    -0.59
    Contin
    -0.56
     sights
    -0.56
     unwanted
    -0.55
    acists
    -0.55
     Vs
    -0.54
     discont
    -0.53
     visions
    -0.53
    POSITIVE LOGITS
     bidder
    0.85
    itored
    0.84
     overseen
    0.80
     mechanism
    0.77
     format
    0.77
    igible
    0.73
     loophole
    0.73
     system
    0.71
    clave
    0.70
    leneck
    0.68
    Act Density 0.432%

    No Known Activations