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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant impact or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a significant positive impact or benefit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esome
    -0.76
     Tags
    -0.75
    smoking
    -0.73
    arians
    -0.70
    nar
    -0.69
    ties
    -0.68
    yx
    -0.67
     Notting
    -0.67
    iris
    -0.67
    onomy
    -0.67
    POSITIVE LOGITS
     appreciated
    1.00
     benefited
    0.94
     amounts
    0.84
     appreci
    0.82
     appreciate
    0.77
     appre
    0.77
     impacting
    0.75
     impacted
    0.75
     effected
    0.75
     simpl
    0.74
    Act Density 0.016%

    No Known Activations