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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal experiences and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -1.01
    nces
    -0.82
     Prosecut
    -0.68
     headquartered
    -0.67
     interviewed
    -0.67
     Canaver
    -0.66
     Petition
    -0.66
     Procedures
    -0.66
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.66
     Opinion
    -0.65
    POSITIVE LOGITS
     castle
    0.77
     eternity
    0.77
     whim
    0.75
     unsuspecting
    0.74
     throats
    0.73
     scenery
    0.71
     throat
    0.70
     roof
    0.69
     pillow
    0.69
     ledge
    0.69
    Act Density 3.672%

    No Known Activations