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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.25
     myſelf
    -1.20
     betweenstory
    -1.20
     CreateTagHelper
    -1.19
     increí
    -1.17
    <unused79>
    -1.16
     indígen
    -1.16
    <unused74>
    -1.16
    <unused41>
    -1.16
    <unused43>
    -1.16
    POSITIVE LOGITS
     
    0.80
    -
    0.76
    ,
    0.76
    .
    0.72
    ↵↵
    0.70
     in
    0.69
     had
    0.69
     and
    0.68
     for
    0.67
    1
    0.66
    Act Density 0.507%

    No Known Activations