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

    Neuronpedia

    INDEX
    Explanations

    terms related to project descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific projects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.76
    umeric
    -0.74
    reviewed
    -0.72
    mony
    -0.72
    iaries
    -0.71
    ense
    -0.67
    ĸļ
    -0.66
    wart
    -0.64
    oft
    -0.64
    brate
    -0.64
    POSITIVE LOGITS
     impending
    0.86
    oneliness
    0.79
     daddy
    0.74
     holidays
    0.71
     dads
    0.71
     upcoming
    0.70
     topic
    0.70
     guy
    0.69
     dangers
    0.68
     similarities
    0.68
    Act Density 0.208%

    No Known Activations