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

    Neuronpedia

    INDEX
    Explanations

    locations or points of reference

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "from there" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chargers
    -0.71
    buster
    -0.63
    mun
    -0.62
    rongh
    -0.59
     ACPI
    -0.58
    aah
    -0.58
     Gian
    -0.57
     AAA
    -0.56
     Suzuki
    -0.56
     bun
    -0.56
    POSITIVE LOGITS
     onwards
    0.75
    ope
    0.75
    ģ«
    0.71
     standpoint
    0.70
    assi
    0.69
    llah
    0.68
    icter
    0.66
    gery
    0.65
     outset
    0.64
    irting
    0.63
    Act Density 0.082%

    No Known Activations