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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarification or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artney
    -0.70
    izoph
    -0.64
    ifice
    -0.60
    ainer
    -0.60
    icidal
    -0.60
     substrate
    -0.59
     lif
    -0.58
    irlf
    -0.57
     spawn
    -0.57
    orum
    -0.56
    POSITIVE LOGITS
     myself
    1.12
    xtap
    0.77
     personally
    0.68
     congr
    0.67
     unres
    0.67
     fortunate
    0.66
    saw
    0.66
     gladly
    0.63
    Ļ½
    0.63
    poke
    0.63
    Act Density 0.470%

    No Known Activations