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

    Neuronpedia

    INDEX
    Explanations

    headlines or titles of news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ò
    -0.80
    thood
    -0.72
    \\\\
    -0.71
    akable
    -0.70
    omics
    -0.69
    @#
    -0.68
    perse
    -0.68
    ����
    -0.68
    ãĥĺ
    -0.66
    ¯
    -0.66
    POSITIVE LOGITS
     implication
    1.21
     report
    1.20
     statement
    1.20
     article
    1.13
     document
    1.08
     spokesperson
    1.08
    resa
    1.08
     allegation
    1.07
     wording
    1.07
    odore
    1.06
    Act Density 0.324%

    No Known Activations