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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tree"

    oai_token-act-pair · gpt-3.5-turbo

    references to trees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OK
    -0.66
     Candidate
    -0.64
    OK
    -0.64
    ISO
    -0.63
    bleacher
    -0.61
     Continued
    -0.61
    Population
    -0.60
     Parenthood
    -0.60
    INESS
    -0.60
    abad
    -0.60
    POSITIVE LOGITS
     tre
    1.17
    uner
    1.03
    asured
    0.97
    asury
    0.95
    bles
    0.95
    bled
    0.94
    bling
    0.91
    gement
    0.91
     gobl
    0.88
    gments
    0.88
    Act Density 0.004%

    No Known Activations