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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passing along information or objects to others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transmission or passing of information, genes, or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.82
    ļé
    -0.75
    trak
    -0.74
    ãĥĥ
    -0.73
    Ĭ
    -0.67
    etsk
    -0.66
    ãĥ¼
    -0.65
    iosity
    -0.60
    ump
    -0.60
    arta
    -0.59
    POSITIVE LOGITS
     unnoticed
    0.76
    etically
    0.75
     leaflets
    0.66
     orally
    0.64
    roleum
    0.64
     Kod
    0.63
     spores
    0.63
    ographically
    0.62
     willingly
    0.61
     generations
    0.61
    Act Density 0.072%

    No Known Activations