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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone leaving a location or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "left" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alist
    -0.90
    wcsstore
    -0.85
    MAT
    -0.82
     Cosponsors
    -0.69
    MpServer
    -0.66
    usting
    -0.65
    intend
    -0.64
    Stretch
    -0.64
    essee
    -0.64
    Deal
    -0.63
    POSITIVE LOGITS
     undone
    1.06
     behind
    0.89
    overs
    0.88
     town
    0.83
     voluntarily
    0.76
     unfinished
    0.75
    auga
    0.74
     abruptly
    0.74
     unexpl
    0.73
    wich
    0.71
    Act Density 0.051%

    No Known Activations