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

    Neuronpedia

    INDEX
    Explanations

    mathematical and scientific terminology related to equations and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vag
    -0.14
     exploit
    -0.14
     stain
    -0.13
    ea
    -0.13
    etty
    -0.13
    -front
    -0.12
    άνα
    -0.12
     Tune
    -0.12
    Pie
    -0.12
     Neb
    -0.12
    POSITIVE LOGITS
     case
    0.27
     caso
    0.24
    case
    0.23
     cases
    0.21
    	case
    0.21
     Case
    0.21
    Case
    0.20
    -case
    0.18
    _case
    0.18
     models
    0.18
    Act Density 0.260%

    No Known Activations