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

    Neuronpedia

    INDEX
    Explanations

    the special character 'ľ'

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ľ' appearing multiple times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condem
    -0.82
    raints
    -0.74
     conduc
    -0.72
     Journals
    -0.70
     reflex
    -0.70
     vulner
    -0.69
     mounts
    -0.68
     apes
    -0.66
     trainers
    -0.66
     transports
    -0.65
    POSITIVE LOGITS
    vernment
    1.21
    uthor
    1.15
    ï¸ı
    1.02
    \-
    0.90
    wow
    0.88
    lean
    0.87
    resh
    0.87
    ternity
    0.86
    ACP
    0.86
    âĶĢâĶĢ
    0.86
    Act Density 0.175%

    No Known Activations