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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'only' followed by a noun or prepositional phrase

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" and its context in phrases indicating limitation or exclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cent
    -0.68
    desc
    -0.65
    insula
    -0.65
    MAP
    -0.64
    mos
    -0.62
    atana
    -0.62
    aviour
    -0.61
    alam
    -0.61
    pad
    -0.60
    bell
    -0.59
    POSITIVE LOGITS
     fitting
    1.14
     natural
    0.93
     logical
    0.89
     fair
    0.81
     prudent
    0.80
    ifiable
    0.73
     conceivable
    0.73
     downhill
    0.71
     uphill
    0.71
     fractions
    0.70
    Act Density 0.050%

    No Known Activations