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

    Neuronpedia

    INDEX
    Explanations

    mentions of speakers at events or conferences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of speakers in the context of a conference or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soldiers
    -0.79
     Devils
    -0.74
     Mines
    -0.69
    ster
    -0.68
    uilt
    -0.65
    hens
    -0.65
     Miner
    -0.62
     Pradesh
    -0.62
     Moss
    -0.61
     Maritime
    -0.60
    POSITIVE LOGITS
     speakers
    1.16
     speaker
    1.07
    voice
    0.97
    hip
    0.91
    phone
    0.91
     voices
    0.87
    speech
    0.84
    glass
    0.81
    hips
    0.79
     presentations
    0.76
    Act Density 0.038%

    No Known Activations