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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to approval and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fortun
    -0.73
     smoot
    -0.73
     Marketable
    -0.73
     photoc
    -0.68
     disrupted
    -0.67
     stomp
    -0.66
    anwhile
    -0.65
     outl
    -0.64
     Tanz
    -0.64
     synd
    -0.64
    POSITIVE LOGITS
    Ļ
    1.60
    ¬
    1.16
    į
    1.11
    ħ
    1.11
    ¤
    1.07
    ª
    1.04
    ĵ
    1.01
    Ĵ
    1.01
    Ĺ
    0.98
    Ĩ
    0.97
    Act Density 0.333%

    No Known Activations