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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job applications and employment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.07
    4:0.33
    5:0.02
    6:0.08
    7:0.14
    8:0.03
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    acebook
    -1.84
    united
    -1.79
    yll
    -1.76
    utenberg
    -1.76
     apart
    -1.60
    BIT
    -1.59
     bounds
    -1.51
    clud
    -1.49
    ctica
    -1.47
    MAT
    -1.46
    POSITIVE LOGITS
     stirring
    1.52
     replacements
    1.48
     favour
    1.42
     reinforcements
    1.40
     unwanted
    1.39
     absentee
    1.36
     favor
    1.34
     scapego
    1.30
     flickering
    1.29
     faulty
    1.29
    Act Density 0.001%

    No Known Activations