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

    Neuronpedia

    INDEX
    Explanations

    words signifying levels and comparisons in various contexts, often relating to scarcity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esion
    -0.15
    lessness
    -0.15
    urus
    -0.14
    ooks
    -0.14
    neau
    -0.14
    IDES
    -0.14
    ìļ°ë¦¬
    -0.14
    apol
    -0.14
    tracer
    -0.14
    림
    -0.13
    POSITIVE LOGITS
     enough
    0.22
    ly
    0.19
    ikt
    0.18
     indeed
    0.17
     across
    0.17
     nhau
    0.16
    fold
    0.16
    ingly
    0.16
    ized
    0.16
    itud
    0.15
    Act Density 0.204%

    No Known Activations