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

    Neuronpedia

    INDEX
    Explanations

    the phrase "at all" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negation or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LU
    -0.70
    jected
    -0.67
    ufact
    -0.63
     Chancellor
    -0.62
    utsche
    -0.59
    selling
    -0.56
    xit
    -0.56
    jun
    -0.55
    lance
    -0.55
    lict
    -0.55
    POSITIVE LOGITS
    ocating
    0.87
     paws
    0.72
     expense
    0.71
    iances
    0.71
     except
    0.70
     seams
    0.69
     glance
    0.67
     hazards
    0.65
     proportions
    0.65
     kinds
    0.63
    Act Density 0.025%

    No Known Activations