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

    Neuronpedia

    INDEX
    Explanations

    phrases related to showing support for or against various causes or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express support for various causes or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.69
     photographed
    -0.68
     fing
    -0.66
    fx
    -0.65
    llo
    -0.65
    orp
    -0.64
    ashtra
    -0.64
    Tracker
    -0.63
    iae
    -0.62
    ways
    -0.62
    POSITIVE LOGITS
     embattled
    0.75
     Mandatory
    0.72
    thood
    0.72
     charities
    0.69
     vested
    0.68
     alternative
    0.68
    gotten
    0.67
     independence
    0.66
     aut
    0.65
     ideals
    0.65
    Act Density 0.117%

    No Known Activations