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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Med", often related to proper nouns like "Medellin" or "medical"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Med" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.84
     innocence
    -0.75
    ģĸ
    -0.68
    holding
    -0.67
    ãģį
    -0.67
     Wilde
    -0.65
    ngth
    -0.65
    !/
    -0.63
    AUT
    -0.63
    roud
    -0.63
    POSITIVE LOGITS
    ications
    1.15
    iterranean
    1.13
    allion
    1.05
    itations
    1.05
    ication
    1.02
    iator
    0.99
    iation
    0.96
    itated
    0.95
    ient
    0.94
    usa
    0.93
    Act Density 0.017%

    No Known Activations