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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions of removal or displacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.18
    inu
    -0.15
    734
    -0.14
    obre
    -0.14
    quo
    -0.14
    Rs
    -0.13
    avax
    -0.13
    bole
    -0.13
    اÙĪÙĬ
    -0.13
     opak
    -0.13
    POSITIVE LOGITS
    ropp
    0.16
    oth
    0.15
    çĬ¯
    0.15
    Cause
    0.15
    orne
    0.14
    rang
    0.14
     Duffy
    0.14
     verv
    0.14
     Sloan
    0.14
    üst
    0.14
    Act Density 0.123%

    No Known Activations