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

    Neuronpedia

    INDEX
    Explanations

    mentions of conventions or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conventions or related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tera
    -0.77
    cam
    -0.68
    lasses
    -0.67
    undai
    -0.66
    bole
    -0.66
    utenberg
    -0.64
    lights
    -0.64
    arma
    -0.63
    erenn
    -0.63
    hner
    -0.63
    POSITIVE LOGITS
    eers
    1.13
     convention
    1.11
     Convention
    0.94
    ally
    0.94
     conventions
    0.88
     hall
    0.81
    arium
    0.80
     delegates
    0.80
    icity
    0.77
    eering
    0.76
    Act Density 0.013%

    No Known Activations