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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships, conditions, or nuances in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    them
    -0.63
    Its
    -0.55
    Everything
    -0.53
     THEM
    -0.53
    thats
    -0.52
    You
    -0.52
    writeField
    -0.51
    They
    -0.51
    didn
    -0.51
    Them
    -0.50
    POSITIVE LOGITS
     there
    1.05
     considerable
    0.98
     care
    0.93
     significant
    0.89
     substantial
    0.85
     certain
    0.84
     additional
    0.84
     careful
    0.82
     some
    0.81
     differences
    0.81
    Act Density 2.125%

    No Known Activations