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

    Neuronpedia

    INDEX
    Explanations

    references to evidence and its strength in various arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.14
    اذ
    -0.13
    xia
    -0.13
    brig
    -0.13
    prise
    -0.13
    ego
    -0.13
    nde
    -0.13
    åį
    -0.13
    ep
    -0.13
    алог
    -0.13
    POSITIVE LOGITS
     gathered
    0.32
     supporting
    0.31
     collected
    0.30
    gather
    0.25
     amassed
    0.25
     backing
    0.25
     accumulated
    0.24
     presented
    0.24
     supportive
    0.24
     supports
    0.23
    Act Density 0.094%

    No Known Activations