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

    Neuronpedia

    INDEX
    Explanations

    places or locations mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "in the" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.70
    CVE
    -0.64
    carry
    -0.64
    rers
    -0.62
    giving
    -0.61
     chau
    -0.58
    rer
    -0.58
    CTV
    -0.57
    rig
    -0.57
    ictive
    -0.55
    POSITIVE LOGITS
    between
    1.01
     somew
    0.90
    pires
    0.89
     eternity
    0.82
     between
    0.82
    vironment
    0.80
     totality
    0.78
     AMERICA
    0.77
     America
    0.75
    ordinate
    0.75
    Act Density 0.145%

    No Known Activations