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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or bureaucratic processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'âĢ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scarlet
    -0.69
     Golem
    -0.69
     Saga
    -0.67
     scattering
    -0.65
     Somerset
    -0.65
     Galile
    -0.63
     Pilgrim
    -0.62
     printing
    -0.61
     casting
    -0.61
     Widow
    -0.60
    POSITIVE LOGITS
    ¹
    0.99
    0.85
     âĢº
    0.84
    âķ
    0.82
    taboola
    0.82
    ¬
    0.81
    ¯
    0.79
    âĢł
    0.78
    î
    0.77
    $
    0.77
    Act Density 0.409%

    No Known Activations