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

    Neuronpedia

    INDEX
    Explanations

    structured data and code snippets, particularly those related to mathematical expressions and programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused52>
    -1.02
    <unused51>
    -1.02
    <unused41>
    -1.02
    <unused43>
    -1.02
    [@BOS@]
    -1.02
    <pad>
    -1.02
    <unused8>
    -1.02
    <unused14>
    -1.02
    <unused68>
    -1.02
    <unused79>
    -1.02
    POSITIVE LOGITS
     sp
    0.36
     pod
    0.34
     ch
    0.33
    <eos>
    0.32
     z
    0.32
    ↵
    0.31
     pri
    0.31
    ↵↵
    0.30
     po
    0.30
     sk
    0.30
    Act Density 0.105%

    No Known Activations