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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duffy
    -0.16
    hist
    -0.16
    agens
    -0.15
    abox
    -0.15
     Dav
    -0.15
    ози
    -0.14
    ilty
    -0.14
    ستاÙĨ
    -0.14
    anko
    -0.14
    ampoo
    -0.14
    POSITIVE LOGITS
     own
    0.21
     Own
    0.15
    lam
    0.15
     CHO
    0.15
    964
    0.15
    Spacer
    0.15
    ana
    0.14
    kowski
    0.14
     entire
    0.14
    undra
    0.13
    Act Density 0.281%

    No Known Activations