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

    Neuronpedia

    INDEX
    Explanations

    references to communication and contact points within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.01
    3:0.12
    4:0.09
    5:0.07
    6:0.04
    7:0.02
    8:0.39
    9:0.08
    10:0.01
    11:0.01
    Negative Logits
     stacked
    -2.02
     Darrell
    -1.81
    installed
    -1.76
     Zed
    -1.73
     Jaw
    -1.69
     Scalia
    -1.68
    align
    -1.64
    rats
    -1.62
    gear
    -1.61
     Fedora
    -1.59
    POSITIVE LOGITS
     contacts
    2.27
     hotline
    2.18
     solicit
    2.16
     exchanges
    2.06
     enqu
    2.03
     Emails
    2.02
     apologise
    1.95
     dialogue
    1.89
     inquiries
    1.88
     lia
    1.86
    Act Density 0.032%

    No Known Activations