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

    Neuronpedia

    INDEX
    Explanations

    words related to physical boundaries or limits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to boundaries or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orah
    -0.84
    ondo
    -0.81
    jury
    -0.78
    fortune
    -0.77
    ocker
    -0.77
    enza
    -0.74
    ulz
    -0.73
    kus
    -0.73
    obe
    -0.73
    milo
    -0.71
    POSITIVE LOGITS
     boundaries
    1.39
     boundary
    1.22
     Bound
    0.90
     markers
    0.86
     barriers
    0.75
     bounds
    0.75
     Limits
    0.75
     thresholds
    0.72
     delim
    0.72
     gates
    0.72
    Act Density 0.011%

    No Known Activations