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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds and their concentrations in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izr
    -0.56
     tyrosine
    -0.53
     grade
    -0.52
    rosine
    -0.51
     Grade
    -0.50
    grade
    -0.49
    GRADE
    -0.48
    Grade
    -0.48
     bribe
    -0.47
    nocache
    -0.46
    POSITIVE LOGITS
     gases
    1.04
     gas
    0.94
     Gases
    0.93
     balloon
    0.90
     itſelf
    0.87
     balloons
    0.82
     gaseous
    0.80
     airspace
    0.80
    ſelf
    0.80
     gás
    0.77
    Act Density 0.526%

    No Known Activations