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

    Neuronpedia

    INDEX
    Explanations

    references to alignment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.65
     vision
    -0.60
     basket
    -0.50
     impression
    -0.50
     flash
    -0.48
     actionPerformed
    -0.47
     perception
    -0.47
     spot
    -0.46
     oversize
    -0.46
     Spot
    -0.45
    POSITIVE LOGITS
    Alignment
    1.23
     Alignment
    1.09
     alignment
    1.02
    Preferences
    0.96
    alignment
    0.93
    aligned
    0.89
     Align
    0.85
     alignments
    0.84
     aligning
    0.82
     ALIGN
    0.82
    Act Density 0.164%

    No Known Activations