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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships and communication dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arthed
    -0.74
    ¶
    -0.68
     unison
    -0.68
     respectively
    -0.67
     §§
    -0.66
     Thou
    -0.58
     Authors
    -0.58
    moil
    -0.57
     collectively
    -0.57
    allel
    -0.56
    POSITIVE LOGITS
     himself
    1.21
    )."
    1.01
     ..."
    0.95
    ),"
    0.91
    .""
    0.91
    ."
    0.89
     âĢ¦"
    0.86
     [
    0.86
    .")
    0.85
    ,"
    0.85
    Act Density 0.898%

    No Known Activations