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

    Neuronpedia

    INDEX
    Explanations

    words related to quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or speech marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nieto
    -0.83
     rall
    -0.76
     accomp
    -0.73
     Tribune
    -0.70
     editor
    -0.69
     Editor
    -0.68
     correspondent
    -0.68
     affiliate
    -0.66
    icz
    -0.66
     Meteor
    -0.66
    POSITIVE LOGITS
    normal
    1.16
    false
    1.14
    official
    1.13
    mere
    1.13
    true
    1.11
    catch
    1.10
    almost
    1.09
    safe
    1.09
    classic
    1.09
    feel
    1.08
    Act Density 0.157%

    No Known Activations