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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to boundaries or limits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orah
    -0.90
    enza
    -0.88
    ondo
    -0.84
    uj
    -0.76
    obe
    -0.76
    kus
    -0.74
    oros
    -0.71
    jury
    -0.70
    rive
    -0.69
    frey
    -0.69
    POSITIVE LOGITS
     boundaries
    1.57
     boundary
    1.37
     markers
    0.92
     Bound
    0.86
     bounds
    0.79
     crossings
    0.75
     limits
    0.74
     barriers
    0.74
     thresholds
    0.74
     borders
    0.74
    Act Density 0.005%

    No Known Activations