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

    Neuronpedia

    INDEX
    Explanations

    phrases with a sense of urgency and direct instructions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal knowledge or persuasive appeals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Plaint
    -0.71
     Canaver
    -0.65
    RESULTS
    -0.65
    aucus
    -0.63
     Defendants
    -0.62
    :[
    -0.60
     '[
    -0.60
    OSP
    -0.60
     IPM
    -0.59
    ropri
    -0.58
    POSITIVE LOGITS
     kidding
    0.81
     ya
    0.79
     blah
    0.76
    !.
    0.73
    cha
    0.73
    !).
    0.72
    ?).
    0.71
     math
    0.69
     maths
    0.67
     gotta
    0.67
    Act Density 0.545%

    No Known Activations