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

    Neuronpedia

    INDEX
    Explanations

    quantifiers that indicate approximations or near amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elif
    -0.16
    ãĥ¥
    -0.15
    orem
    -0.15
    jug
    -0.15
    VERR
    -0.15
    /ui
    -0.15
    å±ħ
    -0.15
    esan
    -0.14
    ÑģÑĮ
    -0.14
     Hicks
    -0.14
    POSITIVE LOGITS
     dozen
    0.20
     exclusively
    0.18
     impossible
    0.16
    ighted
    0.16
     vest
    0.16
     entirely
    0.16
    lich
    0.15
    że
    0.15
     perfect
    0.14
     complete
    0.14
    Act Density 0.062%

    No Known Activations