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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accomplishments or actions

    oai_token-act-pair · gpt-3.5-turbo

    first-person and third-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Magikarp
    -0.70
    availability
    -0.68
     Pros
    -0.67
    IOR
    -0.67
    population
    -0.66
    cases
    -0.64
    GMT
    -0.63
    tones
    -0.63
    wik
    -0.61
    20439
    -0.61
    POSITIVE LOGITS
    're
    0.96
    've
    0.90
     clot
    0.86
     cruc
    0.85
     drank
    0.85
    'll
    0.83
     ain
    0.83
     pray
    0.82
     ate
    0.82
     contrace
    0.81
    Act Density 0.208%

    No Known Activations