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

    Neuronpedia

    INDEX
    Explanations

    words related to being 'like-minded'

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups that share similar beliefs or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVER
    -0.75
    pees
    -0.75
    ARDS
    -0.72
    è¦ļéĨĴ
    -0.72
    adium
    -0.70
    PsyNetMessage
    -0.70
    ILA
    -0.68
    IDS
    -0.68
    apon
    -0.67
    osponsors
    -0.67
    POSITIVE LOGITS
    ness
    1.55
    edly
    1.17
    nesses
    1.13
    minded
    1.02
    ly
    1.00
     zeal
    0.84
     minded
    0.80
    lihood
    0.76
    ingly
    0.75
     prag
    0.74
    Act Density 0.042%

    No Known Activations