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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships and connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    752
    -0.17
    .LINE
    -0.15
     ?><?
    -0.15
    emand
    -0.14
    mtree
    -0.14
    ammer
    -0.14
    izio
    -0.14
    mando
    -0.14
    FIXME
    -0.14
    åŁ¹
    -0.14
    POSITIVE LOGITS
     etc
    0.16
    èĻij
    0.15
     non
    0.14
    avir
    0.14
    agt
    0.14
    olor
    0.14
    akers
    0.14
    eya
    0.14
     fort
    0.13
    oppel
    0.13
    Act Density 0.162%

    No Known Activations