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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Elephant"

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.85
     Kenobi
    -0.74
    raints
    -0.73
    DERR
    -0.71
     Responsibility
    -0.70
    lain
    -0.70
    aldehyde
    -0.69
     Papers
    -0.69
     Sakuya
    -0.66
     Hilton
    -0.66
    POSITIVE LOGITS
    venth
    1.46
    phant
    1.28
    fter
    0.92
    oton
    0.90
    ven
    0.88
    ph
    0.85
    lect
    0.84
    ITH
    0.83
    LECT
    0.82
    azar
    0.81
    Act Density 0.025%

    No Known Activations