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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and specifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "of" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynes
    -0.71
     externalToEVAOnly
    -0.69
     reperto
    -0.66
    beam
    -0.66
    heny
    -0.65
    usb
    -0.63
    raviolet
    -0.60
    istrate
    -0.60
    hattan
    -0.59
    assium
    -0.59
    POSITIVE LOGITS
     sorts
    1.16
     course
    1.10
     ours
    0.87
    course
    0.85
    icial
    0.83
     theirs
    0.82
    sted
    0.80
     yours
    0.79
     hers
    0.75
     origin
    0.75
    Act Density 0.312%

    No Known Activations