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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "warm" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.70
    <unused42>
    -0.68
    <unused74>
    -0.68
    <unused41>
    -0.68
    <unused43>
    -0.68
    <unused23>
    -0.68
    𑄮
    -0.68
     ſeinen
    -0.67
    <unused28>
    -0.67
    <unused20>
    -0.67
    POSITIVE LOGITS
     warm
    0.59
    warm
    0.53
    Warm
    0.50
     Warm
    0.47
     World
    0.46
     request
    0.44
     centered
    0.43
    .
    0.43
    Loader
    0.43
    ,
    0.42
    Act Density 0.185%

    No Known Activations