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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize first achievements or historic milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gre
    -0.17
    ucher
    -0.15
     blank
    -0.15
     Hammer
    -0.15
     Borg
    -0.15
     Buch
    -0.14
     Hell
    -0.14
     Ts
    -0.14
    246
    -0.14
     is
    -0.14
    POSITIVE LOGITS
    lox
    0.16
    ilton
    0.15
    .toolbox
    0.15
    å»ł
    0.15
    .addWidget
    0.15
    LEGRO
    0.14
    iá»ģm
    0.14
    erdale
    0.14
    otation
    0.14
    -urlencoded
    0.14
    Act Density 0.114%

    No Known Activations