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

    Neuronpedia

    INDEX
    Explanations

    buttons and their related attributes in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hi
    -0.42
    Hi
    -0.42
    全
    -0.36
     quite
    -0.35
     Hi
    -0.35
    …
    -0.34
     as
    -0.33
    Hello
    -0.33
     ganz
    -0.33
     go
    -0.32
    POSITIVE LOGITS
    ंदीखरीदारी
    1.09
     queſta
    1.03
     Buttons
    1.03
     ſta
    0.98
     buttons
    0.98
     noDo
    0.96
    IntoConstraints
    0.96
     botões
    0.96
     Infórmanos
    0.95
     ſche
    0.94
    Act Density 0.175%

    No Known Activations