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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bray
    -0.15
    enberg
    -0.15
    ulle
    -0.15
    ukkit
    -0.14
    UNET
    -0.14
    ade
    -0.14
    halb
    -0.14
    vince
    -0.14
    aversable
    -0.14
    rored
    -0.14
    POSITIVE LOGITS
     Trot
    0.16
    SizePolicy
    0.15
     {?>↵
    0.15
    érc
    0.15
    461
    0.14
    eday
    0.14
     èµ
    0.13
     Goose
    0.13
    angler
    0.13
    reira
    0.13
    Act Density 0.414%

    No Known Activations