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

    Neuronpedia

    INDEX
    Explanations

    references to urban environments and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chie
    -1.59
    deal
    -1.57
    yla
    -1.41
    thood
    -1.39
    roma
    -1.36
    rium
    -1.35
    rocy
    -1.33
     annual
    -1.32
    agles
    -1.31
     gradual
    -1.30
    POSITIVE LOGITS
    ¾
    2.01
    ł
    1.96
    µ
    1.89
    Ł
    1.83
    ¼
    1.76
    ¸
    1.73
    ¢
    1.71
    ¦
    1.64
    °
    1.61
    ĸ
    1.61
    Act Density 0.007%

    No Known Activations