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

    Neuronpedia

    INDEX
    Explanations

    phrases related to claims or statements of authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests, claims, and sentiments in discussions or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assemb
    -0.70
    foreseen
    -0.69
     ILCS
    -0.69
    ordinate
    -0.64
    venge
    -0.61
     vulner
    -0.60
    ãĥ£
    -0.60
    inia
    -0.59
     swall
    -0.58
     somet
    -0.58
    POSITIVE LOGITS
     sentiments
    0.76
     notion
    0.72
     outright
    0.68
     Ridley
    0.67
     assumption
    0.66
     drum
    0.66
     notions
    0.65
     earlier
    0.65
     misconception
    0.65
     altogether
    0.64
    Act Density 0.257%

    No Known Activations