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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the character "[" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.49
     
    -0.48
    <eos>
    -0.48
     in
    -0.46
     from
    -0.46
    ↵
    -0.43
    '
    -0.43
    ’
    -0.43
    or
    -0.42
     pas
    -0.42
    POSITIVE LOGITS
     resourceCulture
    1.07
     Efq
    1.06
    ſelf
    1.05
     itſelf
    1.04
    AsUp
    1.02
    ſelves
    0.99
     myſelf
    0.98
    NUMX
    0.96
     Anſ
    0.94
     Theſe
    0.93
    Act Density 0.116%

    No Known Activations