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

    Neuronpedia

    INDEX
    Explanations

    protein interactions in a molecular context

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetitive phrases or structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retali
    -0.85
     oath
    -0.75
     battleground
    -0.73
     veto
    -0.72
     allies
    -0.70
     overth
    -0.70
     Kremlin
    -0.70
     appe
    -0.69
     undercut
    -0.68
     compromising
    -0.68
    POSITIVE LOGITS
    Young
    0.97
    Owner
    0.95
    Courtesy
    0.93
    Loc
    0.93
    TY
    0.90
    Artist
    0.88
    Enlarge
    0.87
    Hidden
    0.86
    His
    0.86
    Interview
    0.84
    Act Density 0.604%

    No Known Activations