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

    Neuronpedia

    INDEX
    Explanations

    terms related to attachment or connection components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDI
    -0.18
    asal
    -0.15
    üst
    -0.14
    rossover
    -0.14
     Entry
    -0.14
    jer
    -0.14
    885
    -0.14
    olk
    -0.14
    antha
    -0.13
    illard
    -0.13
    POSITIVE LOGITS
     attachment
    0.46
     attach
    0.44
     attached
    0.43
     attachments
    0.41
    attachment
    0.40
     attaches
    0.39
    Attached
    0.39
    attached
    0.39
     Attachment
    0.38
     Attached
    0.38
    Act Density 0.215%

    No Known Activations