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

    Neuronpedia

    INDEX
    Explanations

    mentions of financial and governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.33
    3:0.10
    4:0.08
    5:0.04
    6:0.05
    7:0.04
    8:0.07
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     continuum
    -1.71
     endif
    -1.47
     comprom
    -1.39
     confines
    -1.39
     hypothesis
    -1.36
     paradigm
    -1.34
     stiffness
    -1.34
     tradition
    -1.34
     enchantment
    -1.33
     presumption
    -1.32
    POSITIVE LOGITS
    bourg
    1.60
    abouts
    1.56
    soever
    1.56
    umbn
    1.50
    selves
    1.45
    lus
    1.43
    ounces
    1.40
    aband
    1.37
    ovember
    1.36
    guards
    1.36
    Act Density 0.010%

    No Known Activations