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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or reference to a path

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mastercard
    -0.47
     Heineken
    -0.45
    *</
    -0.45
    rakech
    -0.44
     ModelRenderer
    -0.44
    eseed
    -0.43
     noDo
    -0.43
    CreateIndex
    -0.42
    Refriger
    -0.42
    CppMethod
    -0.42
    POSITIVE LOGITS
     along
    1.68
     Along
    1.59
    Along
    1.58
     ALONG
    1.57
    along
    1.56
     entlang
    1.05
     вдоль
    0.96
    沿
    0.94
     lungo
    0.92
    沿着
    0.85
    Act Density 0.077%

    No Known Activations