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

    Neuronpedia

    INDEX
    Explanations

    themes related to social relationships and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'gc
    -0.18
    iminal
    -0.17
    iders
    -0.16
    plusplus
    -0.14
     originating
    -0.14
    ==>
    -0.14
    mart
    -0.14
    orc
    -0.13
    warz
    -0.13
     Origin
    -0.13
    POSITIVE LOGITS
     extends
    0.30
     extend
    0.30
     dates
    0.28
     lie
    0.28
     lies
    0.26
     goes
    0.25
    dates
    0.24
     date
    0.24
     Extend
    0.23
     go
    0.23
    Act Density 0.417%

    No Known Activations