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

    Neuronpedia

    INDEX
    Explanations

    themes related to social dynamics and generational trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     always
    -0.16
    ulet
    -0.15
    standing
    -0.15
    MOOTH
    -0.15
     Always
    -0.14
    ombine
    -0.14
     ALWAYS
    -0.14
     somewhere
    -0.14
    oku
    -0.14
    ç¥Ŀ
    -0.14
    POSITIVE LOGITS
     alike
    0.26
     flock
    0.20
    -es
    0.20
     demanding
    0.18
    pecially
    0.17
     especially
    0.17
     themselves
    0.16
    /custom
    0.16
     increasingly
    0.16
     especialmente
    0.16
    Act Density 0.023%

    No Known Activations