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

    Neuronpedia

    INDEX
    Explanations

    words related to relationships and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ators
    -0.31
    itions
    -0.31
    fully
    -0.28
    ductory
    -0.26
    ition
    -0.26
    lasting
    -0.26
    screen
    -0.25
    enced
    -0.25
    emark
    -0.24
    ise
    -0.24
    POSITIVE LOGITS
    ions
    0.15
    å¨ĺ
    0.15
     Rural
    0.15
    ibly
    0.15
    arer
    0.15
    stances
    0.15
    .appspot
    0.15
    etro
    0.14
    rippling
    0.14
     Xunit
    0.14
    Act Density 0.086%

    No Known Activations