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

    Neuronpedia

    INDEX
    Explanations

    elements related to procedural rules or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.76
     ―――――
    -0.61
     useRouter
    -0.60
     pleaſure
    -0.57
    istically
    -0.56
    muka
    -0.54
    errHandler
    -0.53
     ſee
    -0.52
     moschino
    -0.52
    ể
    -0.52
    POSITIVE LOGITS
    //
    1.01
    
    1.01
    <eos>
    0.93
    BeginContext
    0.77
    ↵↵
    0.71
    ↵↵↵↵
    0.71
    tvguidetime
    0.70
    ↵↵↵
    0.67
    ↵↵↵↵↵
    0.66
     resourceCulture
    0.65
    Act Density 0.252%

    No Known Activations