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

    Neuronpedia

    INDEX
    Explanations

    terms related to the act of removing or getting rid of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eil
    -0.14
    iÄįka
    -0.14
    .defaults
    -0.14
    impl
    -0.14
    oon
    -0.14
    andard
    -0.14
    ei
    -0.14
     průbÄĽhu
    -0.14
    ÑģÑĭ
    -0.14
    eu
    -0.13
    POSITIVE LOGITS
    æİī
    0.25
    /disable
    0.21
    /min
    0.21
    /null
    0.18
    /mit
    0.17
     altogether
    0.16
    æ»ħ
    0.15
    /change
    0.15
    oreach
    0.15
    /add
    0.15
    Act Density 0.039%

    No Known Activations