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

    Neuronpedia

    INDEX
    Explanations

    short phrases or phrases in dialogue that are emotionally charged or impactful

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ascus
    -0.87
    escription
    -0.84
    aker
    -0.73
    æ©
    -0.73
    avorite
    -0.73
    bledon
    -0.70
    eatures
    -0.69
    amsung
    -0.67
    inement
    -0.66
    onial
    -0.64
    POSITIVE LOGITS
     Yeah
    1.53
     Alright
    1.50
     Hmm
    1.35
     Okay
    1.28
    Yeah
    1.27
     Oh
    1.26
     Exactly
    1.22
     Huh
    1.20
     Yep
    1.15
     Nope
    1.12
    Act Density 0.105%

    No Known Activations