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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cooperation or collaboration

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ista
    -0.71
    umbo
    -0.69
    ble
    -0.67
    geons
    -0.64
    geon
    -0.64
    hyde
    -0.63
    unc
    -0.63
    ortal
    -0.62
    agnar
    -0.62
    ysis
    -0.61
    POSITIVE LOGITS
    ness
    0.85
    NESS
    0.74
    ãĤ¤ãĥĪ
    0.72
    nesses
    0.71
    together
    0.66
    isphere
    0.66
    arity
    0.65
     Kurd
    0.63
     Together
    0.63
    footed
    0.63
    Act Density 0.027%

    No Known Activations