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

    Neuronpedia

    INDEX
    Explanations

    terms related to the surroundings or environment

    oai_token-act-pair · gpt-3.5-turbo

    references to the environment and possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onomy
    -0.76
    ital
    -0.71
    idine
    -0.67
    ASS
    -0.65
    rop
    -0.65
    aceous
    -0.64
    lic
    -0.64
     deduct
    -0.63
     lease
    -0.62
    ttle
    -0.62
    POSITIVE LOGITS
    cape
    0.95
     Primordial
    0.78
     Sparks
    0.77
     Staples
    0.75
    pread
    0.73
    creen
    0.73
     Inferno
    0.69
    scape
    0.69
    omething
    0.68
     IMAGES
    0.68
    Act Density 0.021%

    No Known Activations