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

    Neuronpedia

    INDEX
    Explanations

    anonymous citations or mentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of anonymous posting or references to anonymous individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geries
    -0.81
     Gork
    -0.80
    eele
    -0.80
    rums
    -0.71
    lasses
    -0.69
    ++++++++++++++++
    -0.67
     Blasio
    -0.67
    ez
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
    efully
    -0.64
    POSITIVE LOGITS
    Ops
    0.69
     Anonymous
    0.68
    imity
    0.68
    ividual
    0.68
    Party
    0.67
    username
    0.67
     Warfare
    0.66
    Members
    0.66
     hacker
    0.66
     Member
    0.65
    Act Density 0.044%

    No Known Activations