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

    Neuronpedia

    INDEX
    Explanations

    comparative sentences starting with "Just as"

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or expressions of comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meet
    -0.87
    olor
    -0.73
    lique
    -0.70
    ulet
    -0.69
    amen
    -0.69
    mt
    -0.66
    REDACTED
    -0.66
    eters
    -0.64
    multi
    -0.64
    ilia
    -0.63
    POSITIVE LOGITS
     luck
    0.73
     darn
    0.70
    ifiable
    0.70
     lawy
    0.65
     warmed
    0.64
     grounded
    0.64
    hetto
    0.63
     unlucky
    0.62
     unloaded
    0.60
     curiosity
    0.59
    Act Density 0.353%

    No Known Activations