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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships or interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" with high frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.77
    DX
    -0.75
    Times
    -0.74
    ut
    -0.73
    shift
    -0.71
    NVIDIA
    -0.70
    FINE
    -0.67
    zip
    -0.66
    NULL
    -0.64
    busters
    -0.64
    POSITIVE LOGITS
     consequently
    1.29
     furthermore
    1.24
     therefore
    1.21
     moreover
    1.19
     hence
    1.18
     thus
    1.10
     thence
    1.06
     secondly
    1.04
     although
    1.00
     therein
    0.94
    Act Density 0.267%

    No Known Activations