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

    Neuronpedia

    INDEX
    Explanations

    words related to personal experiences and emotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize connection or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ievers
    -0.89
    izards
    -0.76
    wic
    -0.73
    gebra
    -0.72
    urtles
    -0.72
    orks
    -0.71
    ormons
    -0.71
    acly
    -0.70
    ãĥĩãĤ£
    -0.69
    oward
    -0.69
    POSITIVE LOGITS
     ambitions
    1.38
     penchant
    1.34
     aspirations
    1.30
     demeanor
    1.26
     abilities
    1.25
     intentions
    1.23
     accomplishments
    1.21
     livelihood
    1.18
     whereabouts
    1.17
     desires
    1.17
    Act Density 0.231%

    No Known Activations