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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to confidence and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused3>
    -0.91
    <unused41>
    -0.91
    <pad>
    -0.91
    <unused43>
    -0.91
    <unused20>
    -0.91
    <unused52>
    -0.91
    <unused74>
    -0.91
    <unused42>
    -0.91
    [@BOS@]
    -0.91
    <unused32>
    -0.91
    POSITIVE LOGITS
     confidence
    0.58
    cc
    0.46
     wages
    0.43
     searching
    0.42
     confianza
    0.40
     (
    0.40
     
    0.40
     connection
    0.39
     hunting
    0.39
    confidence
    0.38
    Act Density 0.402%

    No Known Activations