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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acceptance and tolerance towards various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mingen
    -0.69
    virons
    -0.67
    Autowired
    -0.64
     avrebbero
    -0.64
     Barker
    -0.63
    toolbox
    -0.63
     devriez
    -0.63
    supra
    -0.62
     Lub
    -0.62
     Иль
    -0.62
    POSITIVE LOGITS
     accept
    2.42
     Accept
    2.27
     accepts
    2.25
     acceptance
    2.23
     accepting
    2.17
     accepted
    2.16
     ACCEPT
    2.13
     Accepting
    2.12
    accept
    2.08
     Acceptance
    2.08
    Act Density 0.071%

    No Known Activations