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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to skyscrapers or buildings reaching great heights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architectural structures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Runner
    -0.76
     Angelo
    -0.73
     Viv
    -0.61
     sovere
    -0.60
    ŃĶ
    -0.59
     abundantly
    -0.59
     Wilde
    -0.59
     Pwr
    -0.58
    berto
    -0.58
    ĺħ
    -0.58
    POSITIVE LOGITS
    hed
    1.67
    hing
    1.63
    hes
    1.48
    hers
    1.47
    eting
    1.35
    her
    1.19
    hens
    1.10
    eters
    1.08
    hen
    1.07
    het
    1.06
    Act Density 0.107%

    No Known Activations