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

    Neuronpedia

    INDEX
    Explanations

    sentences where the writer expresses some level of uncertainty or lack of interest in the topic being discussed

    oai_token-act-pair · gpt-3.5-turbo

    the word "really" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.73
    ultan
    -0.69
    hani
    -0.69
    rones
    -0.69
    voy
    -0.67
    erb
    -0.66
    asers
    -0.66
    icipated
    -0.65
    agents
    -0.65
    tein
    -0.65
    POSITIVE LOGITS
     bothered
    1.05
     bother
    1.02
     anymore
    0.90
     bothering
    0.83
    hin
    0.80
     hurting
    0.76
     bothers
    0.75
     shy
    0.74
     sucked
    0.71
     liked
    0.71
    Act Density 0.031%

    No Known Activations