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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions that involve representing or embodying something

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to embodiment and reflection of values or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.97
    nel
    -0.87
    king
    -0.83
    kie
    -0.77
    ker
    -0.74
    ature
    -0.73
    bies
    -0.73
    neau
    -0.73
    veland
    -0.73
    edo
    -0.73
    POSITIVE LOGITS
     prominently
    0.77
     reflected
    0.71
     Gems
    0.68
     externally
    0.68
     therein
    0.66
     manifestations
    0.66
    ocument
    0.64
    cffffcc
    0.64
     behavi
    0.63
    =#
    0.63
    Act Density 0.038%

    No Known Activations