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

    Neuronpedia

    INDEX
    Explanations

    words related to international or overseas activities

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical terms related to international and foreign contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resil
    -0.67
    eer
    -0.66
     Meter
    -0.62
    essee
    -0.62
    THER
    -0.58
     Peb
    -0.57
    nit
    -0.56
     Hamp
    -0.55
    nex
    -0.54
    ioxide
    -0.54
    POSITIVE LOGITS
    abouts
    0.95
    without
    0.87
     speaking
    0.83
    with
    0.82
     via
    0.79
     unnoticed
    0.76
    within
    0.72
    tics
    0.72
     without
    0.72
    selves
    0.72
    Act Density 0.115%

    No Known Activations