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

    Neuronpedia

    INDEX
    Explanations

    phrases related to remote-controlled devices or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to remote-controlled objects or explosives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utra
    -0.84
    uliffe
    -0.72
     spons
    -0.71
    itant
    -0.69
    reau
    -0.68
    upt
    -0.67
     turnaround
    -0.66
    iola
    -0.65
    isher
    -0.62
    âķIJâķIJ
    -0.62
    POSITIVE LOGITS
     whereabouts
    0.65
    effic
    0.63
    ogens
    0.63
    iae
    0.63
     Antarctica
    0.62
     escapes
    0.62
    abytes
    0.61
    projects
    0.61
     Territories
    0.61
     coli
    0.60
    Act Density 0.706%

    No Known Activations