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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increases and decreases in statistics or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERR
    -0.18
    trand
    -0.17
    lingen
    -0.17
    åĴ²
    -0.15
    ystick
    -0.15
     itemprop
    -0.15
    monds
    -0.15
    zcze
    -0.15
    hya
    -0.15
     Berm
    -0.15
    POSITIVE LOGITS
     division
    0.14
     bin
    0.14
     rare
    0.14
    BIN
    0.13
    ocr
    0.13
    aper
    0.13
     ap
    0.13
     os
    0.13
     Col
    0.13
     oil
    0.13
    Act Density 0.016%

    No Known Activations