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

    Neuronpedia

    INDEX
    Explanations

    pieces of information where there is something to be entered or inputted, such as characters for verification, names, email addresses, pleas, loops, partnerships, premises, and concerts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to entering information or submitting data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.73
    each
    -0.63
    gem
    -0.63
    kick
    -0.63
    uates
    -0.62
     nipples
    -0.61
    installed
    -0.57
     sake
    -0.57
    aintain
    -0.57
    fulness
    -0.57
    POSITIVE LOGITS
     fray
    1.31
     realm
    0.91
     territory
    0.88
    adr
    0.80
    prises
    0.79
     precincts
    0.76
    tainment
    0.75
     bounds
    0.74
    prise
    0.73
     airspace
    0.73
    Act Density 0.110%

    No Known Activations