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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.18
    3:0.29
    4:0.06
    5:0.05
    6:0.05
    7:0.06
    8:0.04
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
     EVER
    -1.68
    "]=>
    -1.49
     '.
    -1.42
    sha
    -1.41
     date
    -1.37
     badge
    -1.36
    letters
    -1.35
    ');
    -1.35
     Ever
    -1.34
     »
    -1.33
    POSITIVE LOGITS
    aeper
    1.65
    etheless
    1.64
    �
    1.58
     unmist
    1.53
    trak
    1.51
     indis
    1.49
    adle
    1.48
     challeng
    1.47
    alore
    1.47
    anke
    1.46
    Act Density 0.004%

    No Known Activations