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

    Neuronpedia

    INDEX
    Explanations

    phrases related to seeking trustworthy news

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express inquiries or searches for trustworthy news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.67
    ciating
    -0.67
    ä¹
    -0.66
    eer
    -0.66
    feeding
    -0.66
    SPONSORED
    -0.65
    feat
    -0.58
    picking
    -0.57
     Mub
    -0.57
    conduct
    -0.57
    POSITIVE LOGITS
     suspic
    0.81
     Ahead
    0.76
    ahead
    0.75
    ãĤ¤ãĥĪ
    0.72
    uez
    0.70
     aft
    0.70
     ahead
    0.69
     forward
    0.65
     alike
    0.65
     rusty
    0.65
    Act Density 0.032%

    No Known Activations