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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions, specifically involving fractions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.81
    
    -0.80
     للمعارف
    -0.71
    mybatisplus
    -0.68
    ConstraintMaker
    -0.65
     laude
    -0.63
    +#+
    -0.62
    acety
    -0.62
     acety
    -0.62
    󠁴
    -0.60
    POSITIVE LOGITS
    require
    0.60
    Large
    0.58
    large
    0.57
    space
    0.53
    LARGE
    0.50
     Large
    0.48
    huge
    0.45
    pink
    0.45
    :=\
    0.44
    bbox
    0.44
    Act Density 1.203%

    No Known Activations