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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions, debates, or arguments

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "there's" used to introduce statements or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Britons
    -0.62
     elector
    -0.60
     cylinders
    -0.56
     Overse
    -0.54
     Lithuan
    -0.54
     estim
    -0.53
     Wise
    -0.53
     calculating
    -0.52
     Pri
    -0.52
     condemned
    -0.52
    POSITIVE LOGITS
    inki
    0.89
    omething
    0.88
    ashtra
    0.84
    aurus
    0.78
    istance
    0.76
    everal
    0.76
    ushi
    0.74
    omew
    0.74
    ometimes
    0.73
    thora
    0.73
    Act Density 0.032%

    No Known Activations