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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or progression toward a point in time or space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Calvo
    -0.80
    5
    -0.70
     pep
    -0.69
    물
    -0.66
    T
    -0.65
     печа
    -0.64
     pan
    -0.64
    ريبة
    -0.63
     cy
    -0.62
     name
    -0.61
    POSITIVE LOGITS
    toward
    2.32
     toward
    2.27
    towards
    2.25
     Toward
    2.25
     Towards
    2.24
     towards
    2.17
    Towards
    2.17
    Toward
    2.03
     hacia
    1.60
     envers
    1.47
    Act Density 0.048%

    No Known Activations