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

    Neuronpedia

    INDEX
    Explanations

    academic titles and professions

    oai_token-act-pair · gpt-3.5-turbo

    references to professors and doctors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPA
    -0.75
     routed
    -0.73
     takeoff
    -0.73
     destro
    -0.69
     pony
    -0.68
    tumblr
    -0.68
     sled
    -0.68
     actionGroup
    -0.67
     tumble
    -0.67
    spir
    -0.66
    POSITIVE LOGITS
    essors
    1.08
     Joseph
    0.84
     Jonathan
    0.79
    agher
    0.79
     Peter
    0.78
     Gabriel
    0.78
     Jorge
    0.78
     Daniel
    0.78
     Timothy
    0.77
     emer
    0.77
    Act Density 0.060%

    No Known Activations