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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to different fields such as sports, politics, economy and culture

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and their related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avers
    -0.73
    clair
    -0.70
     Originally
    -0.67
    olen
    -0.65
    htaking
    -0.65
    aver
    -0.65
    cientious
    -0.65
    staking
    -0.64
    iless
    -0.64
    ierce
    -0.63
    POSITIVE LOGITS
     endeavor
    0.84
     activity
    0.77
     entity
    0.74
     phenomenon
    0.72
     iteration
    0.72
     accomplishment
    0.72
     outing
    0.72
     endeavour
    0.71
     figure
    0.71
     asset
    0.69
    Act Density 0.761%

    No Known Activations