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

    Neuronpedia

    INDEX
    Explanations

    words related to spinning or derivative works

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spin" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.68
    ermott
    -0.66
     Mellon
    -0.63
     Frie
    -0.62
    avis
    -0.61
     Newsp
    -0.60
    essors
    -0.58
     Commodore
    -0.57
     Scores
    -0.57
     Puzz
    -0.57
    POSITIVE LOGITS
    ners
    1.47
    eless
    1.05
    ned
    1.05
    othal
    1.01
    offs
    0.96
    wheel
    0.89
    off
    0.87
    balls
    0.84
    otom
    0.82
    kered
    0.82
    Act Density 0.057%

    No Known Activations