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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lack of effort or interest

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bother" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sung
    -0.82
    oiler
    -0.78
    arta
    -0.75
    arb
    -0.74
    ramer
    -0.73
    ophe
    -0.73
    UE
    -0.70
    anked
    -0.69
    reements
    -0.68
    uts
    -0.68
    POSITIVE LOGITS
     bother
    1.09
     bothering
    1.07
    crow
    0.88
     bothered
    0.81
    some
    0.80
     tamp
    0.75
    fulness
    0.74
    MENTS
    0.74
     bothers
    0.66
    naires
    0.65
    Act Density 0.020%

    No Known Activations