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

    Neuronpedia

    INDEX
    Explanations

    phrases related to joining and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "join" or "joined"

    np_acts-logits-general · gemini-2.0-flash

    join forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.58
    zęd
    -0.54
    Dermott
    -0.54
     Himself
    -0.53
    degard
    -0.52
    berley
    -0.51
     oakley
    -0.51
     QoS
    -0.51
    ācijas
    -0.50
     själva
    -0.50
    POSITIVE LOGITS
     forces
    1.59
    forces
    1.32
     Forces
    1.29
    Forces
    1.22
     FORCES
    1.11
     join
    1.07
     Joining
    1.07
     joins
    1.02
     ranks
    1.01
     joined
    1.01
    Act Density 0.058%

    No Known Activations