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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases that indicate questioning or doubting someone's abilities or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orent
    -0.15
    ers
    -0.15
     Guerr
    -0.15
    phase
    -0.14
     Commons
    -0.14
    ÙĪØŃ
    -0.13
    Ñĥка
    -0.13
    LR
    -0.13
    áºŃu
    -0.13
    oles
    -0.13
    POSITIVE LOGITS
    ozor
    0.17
    ETCH
    0.17
    urious
    0.16
    ên
    0.16
    .assets
    0.16
    uzzer
    0.15
    å¾
    0.15
    æ§ĭ
    0.15
    ¶Į
    0.15
    idelity
    0.15
    Act Density 0.316%

    No Known Activations