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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing inclusion or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.71
     TestBed
    -0.70
    yarnpkg
    -0.67
     förb
    -0.64
     فريبيس
    -0.63
    aktus
    -0.63
     CascadeType
    -0.61
    entibus
    -0.61
     glisser
    -0.60
     IndexPath
    -0.60
    POSITIVE LOGITS
    theless
    0.72
    Secondly
    0.70
    Firstly
    0.65
     Secondly
    0.60
     Firstly
    0.55
    erdings
    0.55
    כשיו
    0.55
     таки
    0.54
    demment
    0.53
     NSCoder
    0.53
    Act Density 0.166%

    No Known Activations