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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to actions, particularly in the present participle form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.07
    3:0.06
    4:0.08
    5:0.04
    6:0.05
    7:0.39
    8:0.04
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    +(
    -1.59
    java
    -1.53
    furt
    -1.52
    SourceFile
    -1.46
    ]+
    -1.45
    hesis
    -1.45
    :-
    -1.43
    abel
    -1.42
    pection
    -1.42
    reatment
    -1.41
    POSITIVE LOGITS
     vault
    2.04
     credentials
    2.03
     treasure
    1.88
     immortality
    1.86
     shelf
    1.79
     laure
    1.79
     passwords
    1.72
    Downloadha
    1.72
     clipboard
    1.72
     riches
    1.71
    Act Density 0.001%

    No Known Activations