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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to work and effort in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RFI
    -0.59
    :✨
    -0.55
     spad
    -0.55
    LookAnd
    -0.54
    ennheiser
    -0.51
    GOTREF
    -0.50
     IKEA
    -0.50
     CCT
    -0.49
     BoxDecoration
    -0.49
     useAuth
    -0.49
    POSITIVE LOGITS
     hard
    0.82
     harder
    0.70
     towards
    0.68
     WORKING
    0.67
     toward
    0.67
     tirelessly
    0.67
     saites
    0.67
    WORKING
    0.66
    hopped
    0.64
     closely
    0.63
    Act Density 0.093%

    No Known Activations