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

    Neuronpedia

    INDEX
    Explanations

    phrases related to office locations and real estate development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.86
    theless
    -0.76
    olini
    -0.72
    âķIJâķIJ
    -0.69
    eful
    -0.69
    MQ
    -0.68
    ivals
    -0.68
    ICAN
    -0.68
    ï¸
    -0.67
     Haram
    -0.66
    POSITIVE LOGITS
    holder
    1.07
    tops
    1.07
    holders
    1.05
    room
    0.94
     365
    0.86
    person
    0.83
     tower
    0.82
    wife
    0.81
    mate
    0.81
     suite
    0.79
    Act Density 0.028%

    No Known Activations