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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to building materials and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific attributes or qualities associated with products or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.77
    iage
    -0.70
    orum
    -0.65
    Semitism
    -0.63
    ENCE
    -0.62
    zsche
    -0.59
    ths
    -0.59
    rahim
    -0.58
    speech
    -0.58
    nings
    -0.57
    POSITIVE LOGITS
     oriented
    1.24
    -
    1.21
     friendly
    1.20
     driven
    1.15
     ridden
    1.13
     compliant
    1.10
     sized
    1.08
     themed
    1.06
     constrained
    1.05
     minded
    1.04
    Act Density 0.744%

    No Known Activations