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

    Neuronpedia

    INDEX
    Explanations

    phrases related to construction, upgrades, and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.77
    mişti
    -0.73
    EndContext
    -0.73
    >{@
    -0.72
    centralwidget
    -0.68
    giveness
    -0.65
    ArgsConstructor
    -0.63
     pylint
    -0.61
    ensuremath
    -0.61
    xymatrix
    -0.61
    POSITIVE LOGITS
    mak
    0.56
     whole
    0.53
     engage
    0.52
    AddTagHelper
    0.51
     Make
    0.49
     ולה
    0.48
    Make
    0.47
     save
    0.46
    ble
    0.46
     Save
    0.46
    Act Density 0.541%

    No Known Activations