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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.00
    2:0.08
    3:0.04
    4:0.05
    5:0.02
    6:0.22
    7:0.19
    8:0.03
    9:0.03
    10:0.18
    11:0.10
    Negative Logits
    ollah
    -1.50
     controversies
    -1.35
     laugh
    -1.28
     temper
    -1.25
     fertilizer
    -1.25
     pomp
    -1.24
     speculate
    -1.24
     inspir
    -1.23
     remedies
    -1.22
     consistency
    -1.22
    POSITIVE LOGITS
    occupied
    1.56
    ombat
    1.53
    76561
    1.43
     Copy
    1.41
    EStream
    1.36
     Enabled
    1.35
    password
    1.35
    coded
    1.34
     Nielsen
    1.34
    acker
    1.33
    Act Density 0.001%

    No Known Activations