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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal introspection and emotional struggles with relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortmund
    -0.73
    atories
    -0.67
    ymm
    -0.65
    ãĥ©ãĥ³
    -0.65
    iaries
    -0.63
    untled
    -0.62
    raft
    -0.62
    cedented
    -0.60
    romeda
    -0.58
    awei
    -0.58
    POSITIVE LOGITS
     fucking
    1.09
     goddamn
    1.09
     fuckin
    1.06
     shit
    0.97
     FUCK
    0.94
     damn
    0.93
     anyways
    0.90
     subconscious
    0.90
     kinda
    0.90
     damned
    0.89
    Act Density 0.572%

    No Known Activations