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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or phrases in quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasers
    -0.77
    Vert
    -0.77
    anders
    -0.77
     Cups
    -0.75
     ankles
    -0.73
     Zombies
    -0.72
    sites
    -0.71
     poisons
    -0.70
     Bots
    -0.70
    lees
    -0.70
    POSITIVE LOGITS
     standpoint
    0.86
    illary
    0.77
    achable
    0.76
    iator
    0.71
    amic
    0.70
    querque
    0.70
     perspective
    0.69
    ixir
    0.66
    atable
    0.66
    iece
    0.66
    Act Density 0.324%

    No Known Activations