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

    Neuronpedia

    INDEX
    Explanations

    words related to tails or tail-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enzo
    -0.75
    равда
    -0.66
     Brunner
    -0.66
    zke
    -0.64
    newInstance
    -0.63
    tium
    -0.62
    спубли
    -0.61
    Brunswick
    -0.60
    Byron
    -0.59
    abadi
    -0.58
    POSITIVE LOGITS
     Tail
    1.88
     tail
    1.76
    tail
    1.73
     TAIL
    1.70
     tails
    1.69
    Tail
    1.66
     Tails
    1.61
    tails
    1.40
    trail
    1.36
    TAIL
    1.35
    Act Density 0.055%

    No Known Activations