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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capability and certain prepositions indicating relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dissipation
    -0.79
     apparaître
    -0.76
     wept
    -0.75
     fevere
    -0.73
     organiser
    -0.71
     Efq
    -0.70
     extrapolated
    -0.69
     Jefus
    -0.69
    orologio
    -0.68
     whistled
    -0.68
    POSITIVE LOGITS
     getting
    1.11
     making
    1.10
     being
    1.08
     having
    1.06
     doing
    1.03
     keeping
    0.99
     using
    0.84
     avoiding
    0.83
     finding
    0.80
     taking
    0.80
    Act Density 0.818%

    No Known Activations