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

    Neuronpedia

    INDEX
    Explanations

    modal and auxiliary verbs in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maxn
    -0.71
     Houſe
    -0.68
    ^(@)
    -0.67
     fevere
    -0.67
    mybatisplus
    -0.66
    izable
    -0.65
     pleaſure
    -0.65
    binaan
    -0.65
     enfans
    -0.64
    UpInside
    -0.63
    POSITIVE LOGITS
     is
    0.84
     also
    0.80
    webElement
    0.69
     has
    0.69
     was
    0.68
     propOrder
    0.64
     always
    0.62
     certainly
    0.60
     will
    0.59
     isn
    0.59
    Act Density 0.875%

    No Known Activations