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

    Neuronpedia

    INDEX
    Explanations

    user identifiers or hashtags

    oai_token-act-pair · gpt-3.5-turbo

    hashtags or labels used in social media posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pestic
    -0.72
     Sov
    -0.70
    ahime
    -0.70
     veh
    -0.70
     weap
    -0.69
    stitial
    -0.69
     horizont
    -0.68
     Wander
    -0.67
     colle
    -0.66
     predec
    -0.66
    POSITIVE LOGITS
    ########
    1.30
    ################################
    1.29
    ################
    1.14
    ###
    0.91
     ##
    0.82
     Posts
    0.82
    nice
    0.79
    region
    0.78
    bitcoin
    0.71
    deck
    0.71
    Act Density 0.007%

    No Known Activations