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

    Neuronpedia

    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.13
    3:0.04
    4:0.13
    5:0.03
    6:0.08
    7:0.22
    8:0.02
    9:0.03
    10:0.08
    11:0.16
    Negative Logits
    DragonMagazine
    -1.62
    nown
    -1.40
    etheless
    -1.36
    20439
    -1.35
    ledged
    -1.33
    kered
    -1.28
    umerable
    -1.28
    vier
    -1.21
    ////////////////////////////////
    -1.20
    ickey
    -1.18
    POSITIVE LOGITS
    sburgh
    1.44
     renov
    1.35
    balance
    1.27
    burgh
    1.27
     pron
    1.26
     reload
    1.25
    enegger
    1.24
     prop
    1.19
    construct
    1.18
     liqu
    1.14
    Act Density 0.015%

    No Known Activations