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

    Neuronpedia

    INDEX
    Explanations

    positive expressions of personal experiences or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mug
    -0.17
    moz
    -0.16
    526
    -0.16
    adera
    -0.15
    527
    -0.15
    mong
    -0.14
    ALA
    -0.14
     mong
    -0.14
    ssel
    -0.14
    ADER
    -0.13
    POSITIVE LOGITS
     mat
    1.08
     Matt
    1.07
     matt
    0.98
     matrix
    0.97
     Mat
    0.96
    mat
    0.95
     MAT
    0.95
    Matt
    0.94
     Matthew
    0.94
     matrices
    0.94
    Act Density 0.061%

    No Known Activations