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

    Neuronpedia

    INDEX
    Explanations

    instances of belonging and responsibility within a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icter
    -0.61
    itaire
    -0.58
     Ambro
    -0.56
    nesday
    -0.55
     Vaugh
    -0.53
     advoc
    -0.52
    asus
    -0.52
    acerb
    -0.51
    aml
    -0.51
    pex
    -0.51
    POSITIVE LOGITS
     themselves
    1.00
     selves
    0.96
    selves
    0.90
    MpServer
    0.64
     mouths
    0.63
     orbits
    0.61
     asses
    0.59
     together
    0.58
     coats
    0.58
     individually
    0.57
    Act Density 0.456%

    No Known Activations