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

    Neuronpedia

    INDEX
    Explanations

    phrases that express willingness to assist or accommodate others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ke
    -0.15
    èm
    -0.15
     pr
    -0.15
     Ashton
    -0.15
     Award
    -0.15
    traction
    -0.14
    eros
    -0.14
    erk
    -0.13
     lev
    -0.13
    que
    -0.13
    POSITIVE LOGITS
    inski
    0.17
    Globals
    0.17
    anter
    0.15
    ÑĥÑĤи
    0.15
    #:
    0.15
    ally
    0.15
    annes
    0.15
    ibase
    0.14
    spacer
    0.14
    à¸Ļาม
    0.14
    Act Density 0.017%

    No Known Activations