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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific special character 'ľ'

    oai_token-act-pair · gpt-3.5-turbo

    specific repeated symbols or non-standard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.90
     similarities
    -0.82
    matic
    -0.80
    writers
    -0.71
    role
    -0.71
     similarity
    -0.68
     primates
    -0.68
    igators
    -0.64
     divisions
    -0.64
     Declaration
    -0.63
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.25
    ľ
    1.16
    à©
    1.02
    ĸ
    0.97
    ZI
    0.95
    ा
    0.94
    Ł
    0.94
    é£
    0.92
    ¼
    0.91
    Ħ
    0.89
    Act Density 0.104%

    No Known Activations