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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Port" followed by a word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ports, particularly Port Authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGHTS
    -0.72
    âķIJâķIJ
    -0.67
    hower
    -0.66
    ãĤŃ
    -0.65
    ãĥ©ãĥ³
    -0.65
    soever
    -0.63
     sund
    -0.63
    pta
    -0.63
    FREE
    -0.62
    gger
    -0.62
    POSITIVE LOGITS
    folios
    1.40
    rait
    1.39
    folio
    1.32
    raits
    1.28
    ugal
    1.02
    ions
    0.91
    eur
    0.89
    als
    0.86
    ilage
    0.81
    ray
    0.81
    Act Density 0.010%

    No Known Activations