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

    Neuronpedia

    INDEX
    Explanations

    words related to official meetings and events

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of meetings, hearings, and public events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     branching
    -0.64
     proven
    -0.64
    ":"/
    -0.63
    alis
    -0.60
     blot
    -0.58
     proof
    -0.58
     workaround
    -0.58
     sin
    -0.58
     gaping
    -0.57
    alys
    -0.57
    POSITIVE LOGITS
     convened
    0.83
    ifiers
    0.80
     held
    0.79
    urion
    0.74
    antry
    0.74
    posium
    0.71
    hops
    0.70
     presided
    0.69
    assembly
    0.69
    icles
    0.66
    Act Density 0.165%

    No Known Activations