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

    Neuronpedia

    INDEX
    Explanations

    quotes and personal remarks

    oai_token-act-pair · gpt-3.5-turbo

    quotes or statements from individuals reflecting on their experiences or memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaults
    -0.84
     mandate
    -0.80
     default
    -0.71
     urgent
    -0.71
    jriwal
    -0.71
    iso
    -0.71
     evasion
    -0.70
     complying
    -0.70
     withdraw
    -0.70
     whining
    -0.69
    POSITIVE LOGITS
    Born
    1.22
    Years
    1.13
     remembers
    1.12
     Born
    1.10
    RIP
    1.09
    His
    1.02
     recalls
    1.01
    Growing
    0.99
    Favorite
    0.98
     Growing
    0.97
    Act Density 0.567%

    No Known Activations