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

    Neuronpedia

    INDEX
    Explanations

    different references to approaches or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soldati
    -0.84
     tys
    -0.73
     Hickey
    -0.71
     Maurer
    -0.66
     cser
    -0.64
    ENAME
    -0.64
     Sulfate
    -0.64
     Sulfur
    -0.63
     arson
    -0.63
     Mur
    -0.63
    POSITIVE LOGITS
     approach
    3.01
     approaches
    2.97
     Approach
    2.88
     APPROACH
    2.78
    Approach
    2.74
    approach
    2.70
     Approaches
    2.60
     approached
    2.35
     approaching
    2.15
     approche
    1.95
    Act Density 0.050%

    No Known Activations