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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating specific conditions or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terms
    -0.19
     Terms
    -0.18
     terms
    -0.18
    Terms
    -0.17
     TERMS
    -0.16
    front
    -0.15
     Replies
    -0.15
    ito
    -0.14
    osl
    -0.14
    ohl
    -0.14
    POSITIVE LOGITS
     connection
    0.23
     writing
    0.21
    writing
    0.19
     Connection
    0.19
     reliance
    0.18
     exceptional
    0.18
     con
    0.18
     Lie
    0.18
     respect
    0.17
    ance
    0.17
    Act Density 0.219%

    No Known Activations