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

    Neuronpedia

    INDEX
    Explanations

    words starting with the letter 'f'

    oai_token-act-pair · gpt-3.5-turbo

    words starting with the letter "f"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paraly
    -0.67
     Boone
    -0.63
     ANGEL
    -0.58
     machine
    -0.57
     aest
    -0.56
    Answer
    -0.56
     messenger
    -0.55
    DOWN
    -0.55
     Lizard
    -0.55
     carriers
    -0.54
    POSITIVE LOGITS
    ruits
    1.25
    urther
    1.25
    actory
    1.25
    eatured
    1.21
    rozen
    1.18
    usion
    1.18
    idelity
    1.18
    antasy
    1.17
    iltration
    1.16
    rost
    1.16
    Act Density 0.047%

    No Known Activations