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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hardware architecture

    oai_token-act-pair · gpt-3.5-turbo

    references to socket types and family-oriented structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.84
    ONEY
    -0.74
    KEY
    -0.70
    Money
    -0.69
     consulted
    -0.69
    zynski
    -0.68
    igl
    -0.65
    quet
    -0.65
    angers
    -0.65
    authorized
    -0.63
    POSITIVE LOGITS
    tenance
    0.88
    lihood
    0.75
     equivalents
    0.69
    ruction
    0.68
    llor
    0.68
    atibility
    0.67
    ohydrate
    0.65
     versions
    0.65
    iste
    0.64
     conversions
    0.64
    Act Density 0.152%

    No Known Activations