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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions relating to interpersonal connections and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asan
    -0.17
    clang
    -0.16
    encial
    -0.16
    ency
    -0.15
     Dome
    -0.15
    å½
    -0.14
     Lag
    -0.14
    cheid
    -0.14
    amen
    -0.14
    unga
    -0.14
    POSITIVE LOGITS
    rosse
    0.17
     faces
    0.16
    faces
    0.15
     Trap
    0.15
     Faces
    0.15
    kins
    0.15
     frozen
    0.14
     facial
    0.14
    reh
    0.14
    mÃŃn
    0.14
    Act Density 0.210%

    No Known Activations