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

    Neuronpedia

    INDEX
    Explanations

    measurements and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akin
    -0.67
     Samar
    -0.63
    reon
    -0.63
     recapt
    -0.61
     Niet
    -0.60
    leased
    -0.60
    agascar
    -0.59
     Giuliani
    -0.59
    osaurus
    -0.58
    abeth
    -0.58
    POSITIVE LOGITS
     diameter
    0.83
    /-
    0.81
    Reply
    0.73
    Ont
    0.69
     tall
    0.69
    !/
    0.69
     spacing
    0.68
     PVC
    0.68
     increments
    0.67
     inch
    0.67
    Act Density 0.036%

    No Known Activations