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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or statements made by characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.75
    construct
    -0.73
    irtual
    -0.70
    bably
    -0.67
    oring
    -0.66
    otine
    -0.66
    appropri
    -0.66
    omnia
    -0.65
    oci
    -0.65
    antine
    -0.65
    POSITIVE LOGITS
    Said
    1.46
    said
    1.39
     said
    1.37
     replied
    1.20
     Says
    1.15
     explained
    1.14
     exclaimed
    1.14
     Said
    1.13
     asked
    1.12
     says
    1.12
    Act Density 0.139%

    No Known Activations