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

    Neuronpedia

    INDEX
    Explanations

    references to arms and arm-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.07
     beſte
    -1.05
    <unused43>
    -1.02
    <unused41>
    -1.02
    <unused74>
    -1.02
    <unused16>
    -1.02
    <unused42>
    -1.02
    <unused47>
    -1.02
    [@BOS@]
    -1.01
    <unused3>
    -1.01
    POSITIVE LOGITS
    t
    0.58
     United
    0.53
    ↵
    0.48
    s
    0.45
     united
    0.45
     was
    0.45
     Got
    0.45
    ↵↵
    0.44
     (
    0.43
     reason
    0.43
    Act Density 0.739%

    No Known Activations