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

    Neuronpedia

    INDEX
    Explanations

    structures or formats related to lists and arrays in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <em>
    -0.79
    in
    -0.75
     
    -0.73
    er
    -0.72
    en
    -0.72
    [toxicity=0]
    -0.70
    z
    -0.68
    <i>
    -0.68
    1
    -0.67
    -
    -0.67
    POSITIVE LOGITS
     myſelf
    1.27
     themſelves
    1.25
     himſelf
    1.24
     poffible
    1.21
     auffi
    1.20
     Jefus
    1.20
     Monfieur
    1.19
     ainfi
    1.15
     purpoſe
    1.13
     neceffary
    1.12
    Act Density 0.145%

    No Known Activations