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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes indicated by the suffix "-ings."

    oai_token-act-pair · gpt-3.5-turbo

    words or concepts related to vague or abstract classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recogn
    -0.69
    URRENT
    -0.67
     dis
    -0.65
     saline
    -0.64
    SIGN
    -0.63
     thin
    -0.62
    UTE
    -0.62
     isol
    -0.61
     sport
    -0.61
     renewable
    -0.60
    POSITIVE LOGITS
    hots
    1.21
    ings
    1.20
    manship
    1.08
    omething
    1.03
    poons
    1.01
    quartered
    1.00
    hower
    0.99
    peed
    0.96
    poon
    0.95
    furt
    0.92
    Act Density 0.014%

    No Known Activations