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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to personal dilemmas and conflicts in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.15
    ãĥ¼ãĥĢ
    -0.15
    ÑģÑĥÑĤ
    -0.15
    apter
    -0.14
     NOTHING
    -0.14
    olit
    -0.14
     EVER
    -0.14
    dont
    -0.13
     ìŀ
    -0.13
    oÅĽci
    -0.13
    POSITIVE LOGITS
     does
    0.47
     DID
    0.47
     DO
    0.45
     DOES
    0.44
     IS
    0.42
     do
    0.41
     did
    0.40
     _
    0.40
     Does
    0.36
    does
    0.35
    Act Density 0.445%

    No Known Activations