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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles with numbers and following the format of '@[Username]'

    oai_token-act-pair · gpt-3.5-turbo

    specific alphanumeric sequences or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrut
    -0.81
    etheless
    -0.75
    puting
    -0.64
     arrang
    -0.63
    urances
    -0.61
     mathemat
    -0.60
    represented
    -0.60
    theless
    -0.60
    conservancy
    -0.58
    athered
    -0.58
    POSITIVE LOGITS
     —
    1.02
    Jr
    0.91
     pic
    0.85
    &
    0.76
    âĢ
    0.76
     CrossRef
    0.76
    uez
    0.73
     ï
    0.72
     âĢ
    0.72
    <|endoftext|>
    0.71
    Act Density 0.040%

    No Known Activations