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

    Neuronpedia

    INDEX
    Explanations

    phrases related to qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     VIDEOS
    -1.19
    heid
    -1.13
    姫
    -1.11
    inas
    -1.05
    INA
    -1.04
    borough
    -1.00
    angelo
    -1.00
    pload
    -1.00
    boa
    -0.94
    ampions
    -0.94
    POSITIVE LOGITS
    liest
    1.24
    etting
    1.22
    etter
    1.04
    liness
    1.00
    lihood
    0.99
    ifier
    0.98
    eren
    0.97
     thing
    0.95
    linger
    0.94
     appro
    0.93
    Act Density 0.439%

    No Known Activations