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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improving or reinforcing various aspects, such as control, security, ties, and relations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of strengthening or enhancing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.76
    Mill
    -0.67
     Marathon
    -0.65
    ilk
    -0.64
    pper
    -0.63
    ppers
    -0.62
     Noon
    -0.61
    ILLE
    -0.61
    ffe
    -0.61
    rez
    -0.61
    POSITIVE LOGITS
    ament
    0.93
     bonds
    0.88
    mble
    0.78
     cohesion
    0.77
     tremend
    0.77
     defences
    0.75
     handshake
    0.75
    atives
    0.75
     ties
    0.74
    nesses
    0.73
    Act Density 0.024%

    No Known Activations