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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to numerical targets and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.07
    4:0.09
    5:0.04
    6:0.06
    7:0.30
    8:0.04
    9:0.04
    10:0.12
    11:0.07
    Negative Logits
     tang
    -1.58
     Orient
    -1.39
     Coliseum
    -1.37
     Queens
    -1.36
    Synopsis
    -1.33
     Brooklyn
    -1.32
     Scene
    -1.31
     smells
    -1.30
     Shape
    -1.30
    burgh
    -1.29
    POSITIVE LOGITS
     allocations
    1.96
     WARN
    1.83
    maximum
    1.73
     allowable
    1.72
     salaries
    1.70
    minimum
    1.68
     budgets
    1.67
     allowances
    1.60
     stip
    1.57
     reimburse
    1.53
    Act Density 0.001%

    No Known Activations