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

    Neuronpedia

    INDEX
    Explanations

    complex patterns or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OIL
    -0.73
    inators
    -0.69
    ablishment
    -0.69
    drops
    -0.66
    HI
    -0.65
    hawks
    -0.64
    IGH
    -0.64
    ï¸
    -0.63
    INST
    -0.63
     Angels
    -0.63
    POSITIVE LOGITS
    ioned
    1.18
    ively
    0.89
     Afric
    0.85
    ions
    0.81
    urally
    0.76
    lly
    0.74
    mble
    0.74
    enegger
    0.69
     twists
    0.68
    iating
    0.67
    Act Density 0.017%

    No Known Activations