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

    Neuronpedia

    INDEX
    Explanations

    concepts related to empathy and interpersonal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «
    -0.15
     Intro
    -0.15
     Aquarium
    -0.14
    iferay
    -0.14
    åľ³
    -0.14
    enko
    -0.14
    .Orientation
    -0.13
    jk
    -0.13
     Canter
    -0.13
     Mercury
    -0.13
    POSITIVE LOGITS
    ford
    0.15
     گرد
    0.15
     surface
    0.15
     paint
    0.14
    vect
    0.14
    Å¡Å¥
    0.14
    iginal
    0.14
    igne
    0.14
    asher
    0.14
    etten
    0.13
    Act Density 0.045%

    No Known Activations