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

    Neuronpedia

    INDEX
    Explanations

    words related to returning or expressing the concept of coming back

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.73
    ghai
    -0.70
    bis
    -0.66
    iop
    -0.64
    chen
    -0.63
    Cola
    -0.61
    urity
    -0.60
    inen
    -0.60
    asm
    -0.58
    stood
    -0.57
    POSITIVE LOGITS
     home
    1.02
    ees
    0.90
    home
    0.88
     HOME
    0.88
     safely
    0.75
     alive
    0.73
    pring
    0.70
    ported
    0.70
     Home
    0.70
    owship
    0.69
    Act Density 0.032%

    No Known Activations