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

    Neuronpedia

    INDEX
    Explanations

    procedural or descriptive transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     căr
    -0.58
     spalle
    -0.57
    bbene
    -0.57
     tarko
    -0.57
     ilmo
    -0.56
    entiary
    -0.54
     religieuses
    -0.54
     låg
    -0.54
     desafios
    -0.54
     giuri
    -0.54
    POSITIVE LOGITS
     become
    1.00
     became
    0.89
     becomes
    0.88
    become
    0.86
     becoming
    0.79
    becomes
    0.73
    became
    0.72
    becoming
    0.72
     Become
    0.70
     Becomes
    0.70
    Act Density 0.283%

    No Known Activations