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

    Neuronpedia

    INDEX
    Explanations

    terms related to service offerings and technical support in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    presumably
    -0.54
     presumably
    -0.54
    umably
    -0.52
     unplayable
    -0.51
     Presumably
    -0.50
     likely
    -0.49
    likely
    -0.48
     poste
    -0.47
     episodic
    -0.47
    weeted
    -0.47
    POSITIVE LOGITS
     proudly
    0.77
     orgull
    0.73
     orgullo
    0.71
     cuidadosamente
    0.70
     prides
    0.70
     Leidenschaft
    0.69
     committed
    0.68
     strives
    0.67
     proud
    0.67
     commitment
    0.67
    Act Density 0.332%

    No Known Activations