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

    Neuronpedia

    INDEX
    Explanations

    verbs related to serving a purpose or role

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating functions or purposes served by various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.79
    clone
    -0.70
    sbm
    -0.69
    razil
    -0.65
    luaj
    -0.63
    vals
    -0.63
    vu
    -0.62
    eros
    -0.60
    las
    -0.60
    ski
    -0.60
    POSITIVE LOGITS
    fully
    0.81
    HTTP
    0.80
    ful
    0.78
     meals
    0.70
    ably
    0.69
    umes
    0.68
    umed
    0.68
     âĶľ
    0.68
    imilation
    0.67
    entials
    0.67
    Act Density 0.029%

    No Known Activations