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

    Neuronpedia

    INDEX
    Explanations

    the word "thing" that is followed by some additional context

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing what is critically important or essential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.75
    inav
    -0.73
    onz
    -0.73
    choes
    -0.70
    ilings
    -0.64
    DOM
    -0.63
    ped
    -0.63
    oufl
    -0.62
    brids
    -0.62
    undai
    -0.61
    POSITIVE LOGITS
     happened
    0.95
    iverse
    0.95
     happening
    0.91
     happens
    0.82
     transpired
    0.80
     missing
    0.76
     undone
    0.75
     bothering
    0.74
     happ
    0.74
     bothers
    0.69
    Act Density 0.033%

    No Known Activations