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

    Neuronpedia

    INDEX
    Explanations

    names and references to a specific person named Jo

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jo," indicating a focus on individuals with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flies
    -0.72
    IFIED
    -0.71
     IMAGES
    -0.69
     interests
    -0.68
     overhead
    -0.66
    oÄŁ
    -0.65
     containment
    -0.65
    ashtra
    -0.64
     amplification
    -0.64
    intendent
    -0.63
    POSITIVE LOGITS
    Jo
    1.29
    aquin
    1.29
    jo
    1.14
    ining
    1.02
    Anne
    0.99
    anne
    0.99
    zeb
    0.98
    anna
    0.98
    aqu
    0.96
    ppa
    0.96
    Act Density 0.015%

    No Known Activations