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

    Neuronpedia

    INDEX
    Explanations

    commands related to persistence and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.01
    ValueStyle
    -0.80
     băr
    -0.78
    Personensuche
    -0.75
    posedge
    -0.74
    digm
    -0.73
     Adamson
    -0.73
     Dorsey
    -0.73
    OGND
    -0.70
    Portale
    -0.70
    POSITIVE LOGITS
     keep
    1.53
    Keeps
    1.49
     KEEP
    1.48
    KEEP
    1.46
    keep
    1.44
     kept
    1.42
     Keep
    1.37
     keeps
    1.36
     Kept
    1.32
    Keep
    1.31
    Act Density 0.032%

    No Known Activations