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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.14
    icable
    -0.14
    umen
    -0.14
    ìĽĶ
    -0.13
    aws
    -0.13
    yre
    -0.13
     fractional
    -0.13
    rench
    -0.13
    opies
    -0.13
    rella
    -0.13
    POSITIVE LOGITS
    unately
    0.22
     reference
    0.21
    reference
    0.21
    Reference
    0.19
    -reference
    0.18
    .reference
    0.18
     Reference
    0.17
    give
    0.16
     anyone
    0.15
     those
    0.15
    Act Density 0.059%

    No Known Activations