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

    Neuronpedia

    INDEX
    Explanations

    words related to physical action or physical activities

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to action sequences or action genre themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gling
    -0.79
    nda
    -0.73
    mbuds
    -0.72
    uran
    -0.71
    YL
    -0.67
    ©¶æ
    -0.67
    reshold
    -0.66
    conservancy
    -0.66
    thening
    -0.66
    è£ħ
    -0.65
    POSITIVE LOGITS
     Replay
    0.79
    ios
    0.74
    bender
    0.74
    tec
    0.74
    ioch
    0.74
    ="/
    0.73
    ãĤ¿
    0.73
    bucks
    0.72
     action
    0.72
     scenes
    0.71
    Act Density 0.021%

    No Known Activations