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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or belief

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating certainty or significance regarding ideas and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Breed
    -0.74
     Outside
    -0.62
    iates
    -0.61
     Gore
    -0.59
    tains
    -0.59
     Umb
    -0.59
     Herm
    -0.58
     Trap
    -0.57
    catch
    -0.56
     Chao
    -0.56
    POSITIVE LOGITS
    ãĥĩãĤ£
    0.74
    ngth
    0.72
    å¦
    0.70
    alde
    0.69
    bsite
    0.68
    $.
    0.67
    Ĥİ
    0.65
    ãĥīãĥ©
    0.65
    æ©
    0.65
    ãĥ´ãĤ¡
    0.65
    Act Density 0.782%

    No Known Activations