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

    Neuronpedia

    INDEX
    Explanations

    phrases in which someone is expressing their thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ò
    -0.85
    à¦
    -0.81
    Synopsis
    -0.79
    rendered
    -0.77
    aceae
    -0.76
    ãĥİ
    -0.74
    Advertisements
    -0.72
    Arab
    -0.72
    SourceFile
    -0.71
    MSN
    -0.71
    POSITIVE LOGITS
     he
    1.08
     there
    0.90
     she
    0.84
     his
    0.81
     although
    0.81
     many
    0.80
     anecd
    0.77
     crews
    0.77
     ideally
    0.76
     it
    0.75
    Act Density 0.196%

    No Known Activations