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

    Neuronpedia

    INDEX
    Explanations

    keywords related to being "free"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being "free."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.80
    liam
    -0.76
    å°Ĩ
    -0.72
    LER
    -0.71
    RAFT
    -0.71
    ENTS
    -0.69
    ourney
    -0.69
    UAL
    -0.68
    igham
    -0.67
     dilig
    -0.66
    POSITIVE LOGITS
    bies
    1.30
    zing
    1.24
    zes
    1.04
    ze
    0.98
    zers
    0.97
    zed
    0.95
    bie
    0.88
    zer
    0.86
    ¥µ
    0.83
    zee
    0.82
    Act Density 0.019%

    No Known Activations