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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantities or numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.05
    4:0.27
    5:0.03
    6:0.04
    7:0.18
    8:0.03
    9:0.04
    10:0.09
    11:0.10
    Negative Logits
    comings
    -1.47
    ciation
    -1.41
    availability
    -1.40
    success
    -1.37
     deployments
    -1.33
     Addiction
    -1.26
    corruption
    -1.26
    ERY
    -1.25
    EStream
    -1.25
    amphetamine
    -1.25
    POSITIVE LOGITS
    quished
    1.62
     stakeholders
    1.53
    rians
    1.42
     supervisors
    1.39
     subsidiaries
    1.39
     volunteers
    1.38
     intermedi
    1.36
     scrut
    1.36
     bystanders
    1.36
     shareholders
    1.35
    Act Density 0.001%

    No Known Activations