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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective action or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to collective or joint actions and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elys
    -0.82
    ysis
    -0.71
    yle
    -0.68
    gery
    -0.67
     privilege
    -0.66
     Ale
    -0.66
     Kelvin
    -0.65
     Guardian
    -0.65
     Gore
    -0.65
     passage
    -0.63
    POSITIVE LOGITS
    umbered
    0.91
    assisted
    0.81
     narrated
    0.80
     identifiable
    0.75
     apologized
    0.75
    gebra
    0.73
     apologize
    0.73
     spaced
    0.72
     separated
    0.72
     speaking
    0.71
    Act Density 0.022%

    No Known Activations