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

    Neuronpedia

    INDEX
    Explanations

    terms related to equivalence and correction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.50
     EconPapers
    -0.44
     décoration
    -0.42
    Incorrect
    -0.39
     TextEditing
    -0.38
     Infórmanos
    -0.38
     seyn
    -0.38
    httphttps
    -0.37
     malheureusement
    -0.37
    incorrect
    -0.37
    POSITIVE LOGITS
     equivalent
    0.82
     underlying
    0.75
     pending
    0.74
     accountability
    0.72
     correction
    0.71
     Underlying
    0.71
    equivalent
    0.68
     accountable
    0.67
     comparable
    0.66
     corrections
    0.66
    Act Density 0.148%

    No Known Activations