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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming, software, and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific descriptors or attributes related to various subject matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.68
    ealous
    -0.64
    inarily
    -0.62
    ivably
    -0.59
    staking
    -0.59
    perate
    -0.58
    Reloaded
    -0.55
     underestimated
    -0.53
    imately
    -0.52
    liest
    -0.51
    POSITIVE LOGITS
    stros
    0.59
     affair
    0.58
     fighter
    0.58
     appliance
    0.57
     sedan
    0.57
     conco
    0.57
     creature
    0.57
     adventure
    0.55
    caster
    0.55
     enclave
    0.54
    Act Density 1.096%

    No Known Activations