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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sounds and auditory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.06
    4:0.10
    5:0.02
    6:0.05
    7:0.45
    8:0.02
    9:0.02
    10:0.08
    11:0.06
    Negative Logits
    profits
    -1.65
    benef
    -1.64
    volent
    -1.62
    ounty
    -1.62
    reon
    -1.61
     altru
    -1.57
    arget
    -1.56
     funding
    -1.56
     Reward
    -1.56
    benefit
    -1.55
    POSITIVE LOGITS
     breeze
    2.18
     footsteps
    2.17
     drums
    1.95
     banging
    1.82
     gunshots
    1.64
     vibrations
    1.62
     voices
    1.62
    dayName
    1.61
     heartbeat
    1.58
     bells
    1.55
    Act Density 0.011%

    No Known Activations