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

    Neuronpedia

    INDEX
    Explanations

    instances of loneliness or self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkin
    -0.16
     dow
    -0.15
    olest
    -0.15
    reu
    -0.14
    illis
    -0.14
     ne
    -0.14
    ubber
    -0.14
    ayla
    -0.13
    obby
    -0.13
     arch
    -0.13
    POSITIVE LOGITS
    /self
    0.18
     ReturnType
    0.15
    istan
    0.15
    /Internal
    0.15
    .Debugger
    0.15
    elf
    0.15
    SELF
    0.14
    .styleable
    0.14
     SELF
    0.14
    Space
    0.14
    Act Density 0.234%

    No Known Activations