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

    Neuronpedia

    INDEX
    Explanations

    phrases containing prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.12
    2:0.05
    3:0.04
    4:0.04
    5:0.12
    6:0.05
    7:0.05
    8:0.11
    9:0.07
    10:0.08
    11:0.10
    Negative Logits
    flix
    -1.55
    anamo
    -1.39
    vine
    -1.32
    unct
    -1.32
    anyahu
    -1.32
    raz
    -1.30
    raviolet
    -1.30
    ject
    -1.26
    wich
    -1.26
    uyomi
    -1.24
    POSITIVE LOGITS
     overall
    1.46
     average
    1.45
     hearts
    1.41
    DERR
    1.32
     discretionary
    1.26
     total
    1.25
     Hearts
    1.24
     Bundes
    1.22
     apprehens
    1.21
    AGES
    1.21
    Act Density 0.011%

    No Known Activations