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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreement or alignment with a situation or idea

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to societal issues and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tripoli
    -0.78
     Dob
    -0.71
     Berm
    -0.67
    arp
    -0.66
     Somers
    -0.66
     Caribbean
    -0.65
     charred
    -0.65
     Appalachian
    -0.64
     Berry
    -0.64
     loft
    -0.64
    POSITIVE LOGITS
    âĢ
    1.61
     âĢ
    1.13
    ."
    0.97
    .�
    0.97
    ðŁĺ
    0.90
    .ãĢį
    0.89
    .''
    0.87
    .""
    0.86
    .
    0.86
    .","
    0.84
    Act Density 0.571%

    No Known Activations