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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving something behind or creating space

    oai_token-act-pair · gpt-3.5-turbo

    references to abundance or a sense of lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.76
    ML
    -0.71
    GW
    -0.71
    NESS
    -0.65
     Strikes
    -0.65
    TT
    -0.61
    ALLY
    -0.61
    aneous
    -0.60
     ML
    -0.60
    GM
    -0.60
    POSITIVE LOGITS
     undone
    1.11
     untouched
    1.09
     footprints
    1.08
     intact
    1.06
     unanswered
    1.01
     behind
    0.98
     unfinished
    0.96
     mark
    0.95
     unexpl
    0.95
     residue
    0.91
    Act Density 0.146%

    No Known Activations