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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or metaphorical boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to physical or metaphorical boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulz
    -0.85
    obe
    -0.80
    asca
    -0.77
    kus
    -0.77
    enza
    -0.76
    fortune
    -0.76
    orah
    -0.76
    ointed
    -0.73
    itous
    -0.71
    akia
    -0.71
    POSITIVE LOGITS
     boundaries
    1.20
     boundary
    1.04
     bounds
    0.85
     Bound
    0.85
     Limits
    0.84
     delim
    0.82
     markers
    0.81
     separating
    0.79
     crossings
    0.78
     limits
    0.77
    Act Density 0.023%

    No Known Activations