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

    Neuronpedia

    INDEX
    Explanations

    commands or phrases related to getting rid of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.88
     actionMode
    -0.86
    ivotopis
    -0.75
    tdessen
    -0.74
    lapsingToolbar
    -0.73
     Forumite
    -0.73
     Bourgoin
    -0.72
    Transkript
    -0.72
     Driscoll
    -0.71
     DMC
    -0.71
    POSITIVE LOGITS
     rid
    1.17
     Rid
    1.07
    Rid
    0.96
     cave
    0.89
     RID
    0.86
     Ramp
    0.85
    rid
    0.80
     Cave
    0.79
     caves
    0.79
    Ramp
    0.78
    Act Density 0.103%

    No Known Activations