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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the creation of various entities or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that specify quantities or characteristics of different concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sung
    -0.72
    gnu
    -0.71
    WARE
    -0.71
    enance
    -0.66
    Constructed
    -0.64
    Bring
    -0.64
    Develop
    -0.63
    Developer
    -0.62
    RESULTS
    -0.62
     Practices
    -0.61
    POSITIVE LOGITS
     havoc
    0.95
     crater
    0.71
     rift
    0.71
     persona
    0.70
     clones
    0.69
    aganda
    0.69
     distinct
    0.68
     Frankenstein
    0.67
     unique
    0.66
     chaos
    0.65
    Act Density 0.199%

    No Known Activations