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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical properties or characteristics such as density

    oai_token-act-pair · gpt-3.5-turbo

    the word "density"

    oai_token-act-pair · gpt-4-turbo

    references to density measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uberty
    -0.78
    opal
    -0.77
     WATCHED
    -0.75
    unes
    -0.74
    bara
    -0.74
    pha
    -0.70
    ña
    -0.70
    ired
    -0.69
    rium
    -0.69
    porary
    -0.69
    POSITIVE LOGITS
     density
    1.11
    density
    0.87
     dens
    0.84
     ratio
    0.84
     ratios
    0.84
     eater
    0.82
     cooker
    0.82
     accelerator
    0.78
     nodd
    0.77
     grocer
    0.76
    Act Density 0.010%

    No Known Activations