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

    Neuronpedia

    INDEX
    Explanations

    references to infrastructure projects and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.74
    Geplaatst
    -0.72
    AxisAlignment
    -0.70
    esgue
    -0.61
    GTCX
    -0.49
     ModelRenderer
    -0.49
     közül
    -0.48
     saites
    -0.46
     FBref
    -0.46
     فريبيس
    -0.45
    POSITIVE LOGITS
     proposed
    1.21
    proposed
    1.00
     planned
    0.97
    Proposed
    0.97
     Proposed
    0.93
     envisioned
    0.91
    PROPOSED
    0.90
     PROPOSED
    0.89
     project
    0.89
     envisaged
    0.83
    Act Density 0.258%

    No Known Activations