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

    Neuronpedia

    INDEX
    Explanations

    mentions of New York City and its surroundings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    batim
    -1.82
    à±į
    -1.64
    ETHOD
    -1.61
    à°¿
    -1.59
    àµį
    -1.57
    áĢ¸
    -1.57
    inco
    -1.51
    à¯ģ
    -1.44
    à¯į
    -1.43
    à±ģ
    -1.41
    POSITIVE LOGITS
    esses
    1.75
    ĩ
    1.51
    itness
    1.50
    eness
    1.40
    ialog
    1.40
    ¤
    1.34
    inates
    1.33
    ħ
    1.33
     command
    1.32
     wings
    1.31
    Act Density 0.131%

    No Known Activations