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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to a single entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "och"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shed
    -0.66
     Tacoma
    -0.64
     Yel
    -0.63
     permission
    -0.62
     Defenders
    -0.61
     à¨
    -0.61
     DMV
    -0.61
    REC
    -0.61
    senal
    -0.61
     kindly
    -0.61
    POSITIVE LOGITS
    och
    1.17
    ilib
    1.06
    orus
    1.05
    ocolate
    1.01
    rane
    1.00
    oe
    0.99
    lear
    0.97
    inese
    0.95
    aos
    0.93
    oly
    0.92
    Act Density 0.005%

    No Known Activations