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

    Neuronpedia

    INDEX
    Explanations

    expressions of acceptance and permissiveness regarding behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nanoTime
    -0.65
     Sou
    -0.62
    ++]=
    -0.62
     calendriers
    -0.60
    verläs
    -0.60
     ElementRef
    -0.57
    ździer
    -0.57
     recruiters
    -0.56
     vigor
    -0.56
    ftar
    -0.55
    POSITIVE LOGITS
     okay
    0.79
     alright
    0.76
    okay
    0.73
     allowed
    0.72
     ok
    0.71
     OKAY
    0.69
    ftagPool
    0.69
     acceptable
    0.66
     acep
    0.65
     OK
    0.64
    Act Density 0.161%

    No Known Activations