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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    words that serve as introductory or transitional phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mate
    -0.64
     lit
    -0.60
     âĢº
    -0.59
     ',
    -0.56
    tered
    -0.56
     virgin
    -0.56
    umbered
    -0.55
     Rodrig
    -0.55
     '.
    -0.55
     Anon
    -0.55
    POSITIVE LOGITS
    Else
    0.80
    mosp
    0.76
    APS
    0.73
    Weak
    0.73
    Quantity
    0.70
    hesda
    0.70
    :(
    0.69
    jriwal
    0.67
    alyst
    0.66
    yrinth
    0.65
    Act Density 0.117%

    No Known Activations