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

    Neuronpedia

    INDEX
    Explanations

    specific pattern of letters in a word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "f"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.72
     messenger
    -0.64
     Bots
    -0.64
     Lizard
    -0.61
     Participant
    -0.60
     Haku
    -0.60
     fringe
    -0.60
     Leopard
    -0.59
     Boone
    -0.59
     Mellon
    -0.58
    POSITIVE LOGITS
    urther
    1.50
    rozen
    1.48
    eatured
    1.44
    actory
    1.40
    amiliar
    1.38
    ederal
    1.38
    avorable
    1.37
    antasy
    1.32
    idelity
    1.31
    iltration
    1.30
    Act Density 0.023%

    No Known Activations