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

    Neuronpedia

    INDEX
    Explanations

    the action of moving or transitioning from one place to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.09
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     Clement
    -2.10
     Ryder
    -2.05
     modelling
    -2.04
     Hurricanes
    -2.02
     Leilan
    -2.01
     Marco
    -2.00
     Mot
    -2.00
     Elias
    -1.99
     raft
    -1.97
     Samson
    -1.97
    POSITIVE LOGITS
    speak
    2.65
    "'
    2.35
    ittle
    2.27
    %"
    2.22
    afety
    2.20
    xc
    2.18
     "%
    2.16
    xff
    2.12
    vae
    2.12
    nesses
    2.11
    Act Density 0.000%

    No Known Activations