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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that indicate a distinction or a level of significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.67
    RTLR
    -0.56
     ModelExpression
    -0.52
    ScopeManager
    -0.52
     SwitchCompat
    -0.51
    Hochspringen
    -0.50
    GEBURTSDATUM
    -0.50
     Wikimedijinoj
    -0.49
     Савезне
    -0.47
    ArrowToggle
    -0.47
    POSITIVE LOGITS
    ukunfts
    0.53
    DebuggerNonUser
    0.47
     Rein
    0.43
    ribbon
    0.42
    ukunft
    0.42
    ürtel
    0.41
     Migrant
    0.40
    guisement
    0.40
     sẻ
    0.40
    mulher
    0.40
    Act Density 0.253%

    No Known Activations