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

    Neuronpedia

    INDEX
    Explanations

    references to the word "tail"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "tail."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.79
    elsen
    -0.74
    psons
    -0.66
    oulos
    -0.66
    Ö¼
    -0.66
    iscopal
    -0.63
    henko
    -0.63
    razil
    -0.62
    rity
    -0.61
     mmol
    -0.60
    POSITIVE LOGITS
    bone
    1.03
     Tail
    1.00
    tail
    0.94
    tails
    0.92
     fins
    0.84
    pole
    0.83
     tail
    0.83
    pipe
    0.81
     tails
    0.80
    wind
    0.74
    Act Density 0.007%

    No Known Activations