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

    Neuronpedia

    INDEX
    Explanations

    words related to taking action or involvement in activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "take" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mith
    -0.61
     Smile
    -0.61
    luaj
    -0.60
    Sphere
    -0.59
     Trees
    -0.59
     coerc
    -0.58
    Pref
    -0.57
     dissatisf
    -0.56
    cape
    -0.56
     Confederacy
    -0.56
    POSITIVE LOGITS
     advantage
    1.09
    aways
    0.95
     care
    0.88
     ACTION
    0.85
     charge
    0.78
    inka
    0.76
     selfies
    0.76
     heed
    0.76
    overs
    0.75
     pains
    0.73
    Act Density 0.105%

    No Known Activations