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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following or tracking actions or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OptionsMenu
    -0.60
    帖最后由
    -0.58
     potest
    -0.56
    Tembelea
    -0.56
     BoxFit
    -0.56
    cadora
    -0.53
    astă
    -0.52
    конец
    -0.49
    audiovisuel
    -0.49
     kontra
    -0.49
    POSITIVE LOGITS
     suit
    1.52
     closely
    1.21
    suit
    1.04
    Suit
    0.97
     footsteps
    0.96
     suite
    0.94
     Suit
    0.94
    suits
    0.83
     suits
    0.82
    AndEndTag
    0.74
    Act Density 0.164%

    No Known Activations