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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of publishing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of publishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llan
    -0.88
    xa
    -0.75
    enhagen
    -0.73
    nea
    -0.71
    bones
    -0.70
    mer
    -0.69
    ugh
    -0.69
    phant
    -0.68
     awoken
    -0.66
     awakened
    -0.65
    POSITIVE LOGITS
    lishing
    1.21
    lisher
    1.06
     excerpts
    0.96
    lishes
    0.87
     publication
    0.79
     publishing
    0.78
     journal
    0.77
     journals
    0.76
     Journals
    0.75
     anonymously
    0.74
    Act Density 0.054%

    No Known Activations