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

    Neuronpedia

    INDEX
    Explanations

    phrases describing movement through physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irst
    -0.70
    CTV
    -0.70
    IF
    -0.69
    Ring
    -0.68
    ADD
    -0.68
    DN
    -0.68
    juven
    -0.67
    pie
    -0.66
    fact
    -0.64
    rising
    -0.62
    POSITIVE LOGITS
     Sussex
    0.76
     Rodrig
    0.72
    esville
    0.71
     Portsmouth
    0.69
     Vik
    0.67
     Examination
    0.66
     Scandinav
    0.65
     clenched
    0.65
     Appalach
    0.64
     waivers
    0.64
    Act Density 0.044%

    No Known Activations