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

    Neuronpedia

    INDEX
    Explanations

    terms related to alignment in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithMany
    -0.64
    /*
    -0.61
    ContentLoaded
    -0.61
    Aholisi
    -0.60
     Audiodateien
    -0.59
    ẵng
    -0.59
     himo
    -0.58
     Josephus
    -0.57
     ModelExpression
    -0.57
    
    -0.57
    POSITIVE LOGITS
     alignment
    1.00
     aligned
    0.90
     Alignment
    0.87
    posedge
    0.85
     align
    0.83
     ALIGN
    0.81
     aligning
    0.81
     Align
    0.78
    alignment
    0.74
     aligns
    0.74
    Act Density 0.076%

    No Known Activations