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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amplify
    -0.20
     unr
    -0.18
    voke
    -0.16
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.15
     ming
    -0.15
     ampl
    -0.15
     nud
    -0.15
     revis
    -0.15
     fou
    -0.15
    pone
    -0.15
    POSITIVE LOGITS
     recess
    0.16
     venture
    0.15
     conduct
    0.15
     conven
    0.14
     illicit
    0.14
    bare
    0.14
     implement
    0.14
    typings
    0.14
    _defs
    0.14
    zeitig
    0.13
    Act Density 3.956%

    No Known Activations