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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditionality or causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Überg
    -0.39
     Konsequ
    -0.39
    -0.38
    imageshack
    -0.35
     magique
    -0.34
     Verpflich
    -0.34
    czeń
    -0.33
     Zustimmung
    -0.32
     propOrder
    -0.32
    Спољашње
    -0.31
    POSITIVE LOGITS
    aarrggbb
    0.59
    hyrchwyd
    0.56
     OMITBAD
    0.54
    antMatchers
    0.53
    BeginContext
    0.53
    Diweddarwch
    0.53
    fillType
    0.52
     NgModule
    0.52
    libft
    0.51
    __))
    0.51
    Act Density 1.813%

    No Known Activations