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

    Neuronpedia

    INDEX
    Explanations

    references to physical cabins or locations containing the word "cabin."

    oai_token-act-pair · gpt-3.5-turbo

    references to "cabin" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inition
    -0.89
    ESCO
    -0.80
    eatures
    -0.78
    enced
    -0.75
    sburgh
    -0.75
    emale
    -0.73
    owship
    -0.73
    encers
    -0.72
    isle
    -0.71
    idel
    -0.71
    POSITIVE LOGITS
    geon
    0.79
     Mock
    0.65
    witch
    0.64
     Designs
    0.64
     depress
    0.63
    etry
    0.61
    Gear
    0.60
    uscript
    0.60
    âĶģ
    0.59
    daq
    0.59
    Act Density 0.100%

    No Known Activations