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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feelings, opinions, and actions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.77
    teness
    -0.67
    livion
    -0.66
    ousing
    -0.62
     entirety
    -0.62
    iciency
    -0.61
    txt
    -0.61
    fty
    -0.60
    hner
    -0.59
    gart
    -0.59
    POSITIVE LOGITS
     compared
    0.91
     interacts
    0.83
     differs
    0.80
     interacting
    0.80
     affects
    0.79
     compares
    0.78
     versus
    0.77
     nowadays
    0.74
     geographically
    0.73
     differently
    0.72
    Act Density 0.153%

    No Known Activations