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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãn
    -0.19
    elight
    -0.15
    cents
    -0.15
    ecs
    -0.15
    ego
    -0.15
    ekim
    -0.15
     бал
    -0.15
    ault
    -0.14
    ufs
    -0.14
    anova
    -0.14
    POSITIVE LOGITS
    609
    0.15
     Starr
    0.14
    oby
    0.14
     Thorn
    0.14
    ovky
    0.14
     Past
    0.13
    368
    0.13
     Swan
    0.13
    arrison
    0.13
    ll
    0.13
    Act Density 0.139%

    No Known Activations