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

    Neuronpedia

    INDEX
    Explanations

    assertive statements involving human actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing personal rights and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bells
    -0.78
     giants
    -0.71
     platforms
    -0.67
     necks
    -0.67
     privatization
    -0.66
     scanners
    -0.66
     pipelines
    -0.65
     corridors
    -0.64
     markets
    -0.64
     divisions
    -0.64
    POSITIVE LOGITS
    coni
    0.82
     Gamble
    0.76
    opausal
    0.76
    ardless
    0.75
    owe
    0.66
     instinctively
    0.66
    abe
    0.66
    odge
    0.65
    register
    0.64
    puter
    0.63
    Act Density 0.384%

    No Known Activations