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

    Neuronpedia

    INDEX
    Explanations

    sentences that provide instructions or steps to follow in a process

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "we" indicating collaborative or collective language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forms
    -0.70
    âĺħâĺħ
    -0.59
     Organizations
    -0.59
    Contents
    -0.58
     FEC
    -0.57
    Times
    -0.57
     Crest
    -0.57
     srfAttach
    -0.56
     Amar
    -0.56
     Notting
    -0.56
    POSITIVE LOGITS
    're
    1.07
    've
    1.07
    ird
    1.05
    eding
    1.02
    ighed
    0.98
     assume
    0.98
    'll
    0.98
    IRD
    0.92
    arers
    0.92
    'd
    0.91
    Act Density 0.202%

    No Known Activations