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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "find" or related forms, indicating a focus on discovery or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.57
     contextLoads
    -0.49
    ⏪
    -0.48
    loài
    -0.48
     Италијани
    -0.47
     chronologically
    -0.47
     mahd
    -0.47
    nissen
    -0.46
     departe
    -0.46
    hasOwnProperty
    -0.45
    POSITIVE LOGITS
     solace
    1.00
     comfort
    1.00
     themselves
    0.92
     himself
    0.91
    themselves
    0.89
     ourselves
    0.86
     herself
    0.86
     yourself
    0.84
     myself
    0.84
     strength
    0.83
    Act Density 0.084%

    No Known Activations