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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity or singularity

    oai_token-act-pair · gpt-3.5-turbo

    the term "sole" and its variations indicating exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.78
     horm
    -0.75
     Machines
    -0.69
     Drugs
    -0.68
     Caf
    -0.66
    CDC
    -0.64
     Everywhere
    -0.63
     Nurs
    -0.61
     Alive
    -0.61
     Disorders
    -0.61
    POSITIVE LOGITS
     propriet
    1.18
     sole
    0.89
    toe
    0.86
    handedly
    0.82
    icular
    0.81
    teenth
    0.80
    mn
    0.79
    ieth
    0.78
     reliance
    0.76
     superpower
    0.76
    Act Density 0.022%

    No Known Activations