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

    Neuronpedia

    INDEX
    Explanations

    an indication of preference or approval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "if you like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.80
    arta
    -0.75
    bourne
    -0.75
    esi
    -0.73
    ells
    -0.72
    Dispatch
    -0.70
    doi
    -0.70
    anthrop
    -0.69
    inion
    -0.69
    chin
    -0.68
    POSITIVE LOGITS
    lihood
    1.43
    lier
    1.01
    liest
    1.00
    ably
    0.88
    liness
    0.84
    minded
    0.80
     ours
    0.76
    glers
    0.75
    76561
    0.69
    terday
    0.67
    Act Density 0.066%

    No Known Activations