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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observing things closely

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closely" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.85
     Mania
    -0.70
    ule
    -0.70
     Bucket
    -0.69
    nos
    -0.67
    amaz
    -0.66
     Jackets
    -0.65
    IRO
    -0.65
    ista
    -0.65
    DIT
    -0.64
    POSITIVE LOGITS
     aligned
    0.95
     minded
    0.91
     cropped
    0.86
    wired
    0.85
     scrutin
    0.83
    minded
    0.83
     resembles
    0.82
     enough
    0.82
     closely
    0.82
     intertwined
    0.82
    Act Density 0.008%

    No Known Activations