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

    Neuronpedia

    INDEX
    Explanations

    references to "sides" or "side" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maker
    -0.20
    ey
    -0.18
     Mayer
    -0.17
    soever
    -0.17
    makers
    -0.17
    shire
    -0.17
    phere
    -0.16
    self
    -0.16
    lied
    -0.16
     sake
    -0.16
    POSITIVE LOGITS
    kick
    0.29
    jÅ¡ÃŃ
    0.22
    arm
    0.20
    ploy
    0.18
    /back
    0.18
    -effects
    0.17
    erin
    0.17
    burn
    0.17
    /front
    0.16
    /all
    0.15
    Act Density 0.057%

    No Known Activations